© 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. 17-LLAMASCOPE-RES-131K
    11. 16138
    Prev
    Next
    INDEX
    Explanations

    Java syntax related to Parcelable interface implementation

    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
    èĿ
    -0.08
    amil
    -0.07
    icut
    -0.07
    ozem
    -0.06
    áºŃy
    -0.06
     Clearance
    -0.06
    úsqueda
    -0.06
    GIN
    -0.06
    íĬľ
    -0.06
    atar
    -0.06
    POSITIVE LOGITS
    .ManyToMany
    0.07
    esty
    0.06
    ason
    0.06
     Det
    0.06
    fax
    0.06
     aliqu
    0.06
     punct
    0.06
    £¼
    0.06
    ÃŃf
    0.05
    })();↵
    0.05
    Activations Density 0.001%

    No Known Activations