© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 16-LLAMASCOPE-RES-32K
    6. 20728
    Prev
    Next
    INDEX
    Explanations

    references to specific years and dates

    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
    childs
    -0.17
    ena
    -0.15
    abe
    -0.14
    ize
    -0.14
     Hayes
    -0.13
    ška
    -0.13
    views
    -0.13
    antee
    -0.13
     entityType
    -0.13
    isch
    -0.13
    POSITIVE LOGITS
    _exe
    0.15
    orca
    0.15
    hoot
    0.15
    /pages
    0.15
    enced
    0.15
    tl
    0.15
     Bits
    0.15
    Ïĥον
    0.14
    _ANGLE
    0.14
    нÑĮ
    0.14
    Activations Density 0.043%

    No Known Activations