© 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. 84584
    Prev
    Next
    INDEX
    Explanations

    mentions of community support and initiatives

    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
     apparently
    -0.06
     deeds
    -0.06
     allegedly
    -0.06
     supposedly
    -0.06
    ι
    -0.06
    aters
    -0.06
    EMPL
    -0.05
    ]){
    -0.05
    cott
    -0.05
     vener
    -0.05
    POSITIVE LOGITS
     our
    0.09
    andal
    0.08
    porto
    0.07
     ourselves
    0.07
     zipcode
    0.07
    ockey
    0.07
     našich
    0.07
    ÏĩÏİ
    0.07
    zew
    0.06
    Ø·Ùħ
    0.06
    Activations Density 0.000%

    No Known Activations