© 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. 5-LLAMASCOPE-RES-131K
    6. 125968
    Prev
    Next
    INDEX
    Explanations

    references to colleagues and coworker relationships

    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
    resse
    -0.07
    lage
    -0.07
    dzi
    -0.06
    achu
    -0.06
    roc
    -0.06
     Residential
    -0.06
    лой
    -0.06
    cho
    -0.06
    ucz
    -0.06
    loh
    -0.06
    POSITIVE LOGITS
     hi
    0.08
     actionTypes
    0.07
    inges
    0.07
    hi
    0.06
    alg
    0.06
    827
    0.06
    ÐĴС
    0.06
    _than
    0.06
    136
    0.06
    iates
    0.06
    Activations Density 0.004%

    No Known Activations