Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 106537
    Prev
    Next
    INDEX
    Explanations

    phrases related to interactions and social contexts

    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
    opup
    -0.07
    ernet
    -0.07
    ucha
    -0.07
    ActivityResult
    -0.07
    OfSize
    -0.07
    aternity
    -0.06
    تب
    -0.06
    以æĿ¥
    -0.06
    marvin
    -0.06
    ocker
    -0.06
    POSITIVE LOGITS
     publicly
    0.10
     public
    0.09
     presence
    0.09
     Presence
    0.08
    .public
    0.08
     público
    0.08
     watched
    0.08
    Presence
    0.08
    public
    0.08
    åħ¬å¼Ģ
    0.08
    Activations Density 0.032%

    No Known Activations