© 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. 3-LLAMASCOPE-RES-32K
    11. 3637
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pass" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lek
    -0.16
    addError
    -0.15
    aille
    -0.15
     дÑĥÑĪ
    -0.15
    iske
    -0.15
     paran
    -0.15
    curacy
    -0.15
    íļĮ
    -0.14
    имÑĥ
    -0.14
    locker
    -0.14
    POSITIVE LOGITS
     Royals
    0.16
    ico
    0.16
    ali
    0.14
    akin
    0.14
    ynchronous
    0.14
    EGA
    0.14
    .ndim
    0.14
     Roy
    0.14
     Liberation
    0.14
    διο
    0.14
    Activations Density 0.015%

    No Known Activations