© 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. 29-LLAMASCOPE-RES-32K
    6. 4028
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fill" and its variations in the context of completing tasks or forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eco
    -0.19
    eff
    -0.18
    onto
    -0.17
    sak
    -0.15
    undo
    -0.15
    efined
    -0.15
    cesso
    -0.15
    feas
    -0.15
    unto
    -0.15
     Thumb
    -0.15
    POSITIVE LOGITS
    ings
    0.23
     gaps
    0.23
    -in
    0.23
    llll
    0.20
    ament
    0.20
     prescriptions
    0.20
     void
    0.20
    ,void
    0.19
    -gap
    0.18
     gap
    0.18
    Activations Density 0.032%

    No Known Activations