© 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. 16619
    Prev
    Next
    INDEX
    Explanations

    code snippets related to SQL database operations and object-oriented programming methods

    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
    ìĩ
    -0.07
     suche
    -0.07
    âl
    -0.07
     ""},↵
    -0.07
    zie
    -0.07
    PRINTF
    -0.07
     vere
    -0.07
     localVar
    -0.06
    sonian
    -0.06
    lds
    -0.06
    POSITIVE LOGITS
    ains
    0.07
    åĩ
    0.06
    AccessType
    0.06
    atem
    0.06
    inox
    0.06
    ìĤ¬ë¬´
    0.06
     Dit
    0.05
    adows
    0.05
     Gamb
    0.05
     moh
    0.05
    Activations Density 0.001%

    No Known Activations