© 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. 2-LLAMASCOPE-RES-32K
    6. 5601
    Prev
    Next
    INDEX
    Explanations

    terms related to legal qualifications or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INU
    -0.15
    nie
    -0.15
     Guth
    -0.15
     Mothers
    -0.14
     familiar
    -0.14
    autoload
    -0.14
     nutrition
    -0.14
    eenth
    -0.14
    ิà¸ķย
    -0.13
    itar
    -0.13
    POSITIVE LOGITS
     Thưá»Ŀng
    0.16
    ume
    0.16
    ussian
    0.15
    ndl
    0.15
    isdiction
    0.15
    ä»
    0.14
     DISCLAIM
    0.14
     volunte
    0.14
    ODO
    0.14
    elps
    0.14
    Activations Density 0.016%

    No Known Activations