© 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. 17-LLAMASCOPE-RES-131K
    6. 3246
    Prev
    Next
    INDEX
    Explanations

    boolean values and numerical data related to algorithms and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hou
    -0.08
    bserv
    -0.08
    ãģ¨ãģĦ
    -0.08
    isas
    -0.07
    .scalablytyped
    -0.07
    ANTE
    -0.07
    formace
    -0.07
    ONUS
    -0.07
    hone
    -0.07
    ãģķãģ¾
    -0.07
    POSITIVE LOGITS
    ,
    0.08
    /no
    0.06
    |
    0.06
    owo
    0.06
     Norris
    0.06
    fy
    0.05
     Forces
    0.05
    &
    0.05
     forces
    0.05
     har
    0.05
    Activations Density 0.012%

    No Known Activations