© 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. 16-LLAMASCOPE-RES-32K
    11. 465
    Prev
    Next
    INDEX
    Explanations

    recurring themes or concepts that highlight commonalities or frequent occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phan
    -0.16
    moz
    -0.16
    thag
    -0.14
    uren
    -0.14
    anz
    -0.14
    ray
    -0.14
    Æ°á»Łng
    -0.14
    ÑĤоÑĦ
    -0.14
    mtree
    -0.13
    /th
    -0.13
    POSITIVE LOGITS
    wealth
    0.30
     xuyên
    0.26
    ly
    0.22
    /common
    0.21
    -used
    0.20
    -place
    0.19
    ality
    0.19
    mente
    0.18
     denominator
    0.18
    alties
    0.18
    Activations Density 0.022%

    No Known Activations