© 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. 71491
    Prev
    Next
    INDEX
    Explanations

    references to data structures, specifically the ArrayList

    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
    renom
    -0.09
    ulen
    -0.08
    indow
    -0.08
    untu
    -0.08
    Disposition
    -0.07
    ÏĮ
    -0.07
    forman
    -0.07
    رÙĩ
    -0.07
    ystate
    -0.07
    astle
    -0.07
    POSITIVE LOGITS
    }elseif
    0.07
    eration
    0.06
    hammer
    0.06
    etti
    0.06
     Said
    0.06
    iti
    0.05
     Any
    0.05
     Consolid
    0.05
     ins
    0.05
     Marg
    0.05
    Activations Density 0.001%

    No Known Activations