© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-32K
    11. 3
    Prev
    Next
    INDEX
    Explanations

    locational descriptors and spatial references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating specific on-screen UI positions, especially corner and upper/lower left/right location descriptors.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĪев
    -0.16
    onas
    -0.16
    OMPI
    -0.16
    reur
    -0.16
    inou
    -0.15
    eniz
    -0.15
    uch
    -0.14
    abis
    -0.14
    ahoma
    -0.14
    287
    -0.14
    POSITIVE LOGITS
    til
    0.16
     Wolff
    0.16
    argas
    0.15
     vấn
    0.15
    .decorate
    0.15
    borg
    0.14
    ATE
    0.14
    ten
    0.13
    -Compatible
    0.13
    ect
    0.13
    Activations Density 0.018%

    No Known Activations