© 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. 12-LLAMASCOPE-RES-32K
    6. 29770
    Prev
    Next
    INDEX
    Explanations

    phrases and questions related to "how about" and discussions in conversational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oras
    -0.15
    nelle
    -0.14
    249
    -0.14
    ãĤ¸ãĤ¢
    -0.14
    ROWS
    -0.14
    ereotype
    -0.13
    åī²
    -0.13
    знаÑĩа
    -0.13
    .office
    -0.13
    ippo
    -0.13
    POSITIVE LOGITS
    emetery
    0.14
    arts
    0.14
    ECT
    0.14
    ares
    0.14
     Reverse
    0.13
     reverse
    0.13
    .locals
    0.13
    upertino
    0.13
     VIR
    0.13
     pick
    0.13
    Activations Density 0.022%

    No Known Activations