© 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. 5-LLAMASCOPE-RES-131K
    11. 126003
    Prev
    Next
    INDEX
    Explanations

    names and titles associated with individuals

    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
    licken
    -0.07
    ilik
    -0.06
    à¥Įà¤Ĥ
    -0.06
    \\\
    -0.06
     Stark
    -0.06
    lik
    -0.06
    .ua
    -0.06
    lasting
    -0.06
    lisi
    -0.06
    ipa
    -0.05
    POSITIVE LOGITS
    urer
    0.07
    pace
    0.07
    isd
    0.06
    ENO
    0.06
    eno
    0.06
    izador
    0.06
    awesome
    0.06
    üre
    0.06
    uent
    0.06
    uer
    0.06
    Activations Density 0.041%

    No Known Activations