© 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. 17-LLAMASCOPE-RES-32K
    11. 21688
    Prev
    Next
    INDEX
    Explanations

    references to frequency or intervals of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abox
    -0.16
    rella
    -0.16
    ÑĪин
    -0.15
    hait
    -0.15
    sher
    -0.15
    _DEAD
    -0.15
    mare
    -0.14
    ceu
    -0.14
    иÑĤоÑĢ
    -0.14
    kin
    -0.14
    POSITIVE LOGITS
    ater
    0.17
    arto
    0.15
     Mos
    0.15
    ãĤĪãģĨãģ§ãģĻ
    0.15
     eg
    0.15
    erten
    0.14
    531
    0.14
     intervals
    0.14
     sacr
    0.14
    RL
    0.14
    Activations Density 0.038%

    No Known Activations