Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40450
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of separation or parting from others

    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
    erli
    -0.08
     dikke
    -0.08
    пон
    -0.08
     zwarte
    -0.08
    tru
    -0.08
    /key
    -0.07
    zet
    -0.07
    elda
    -0.07
    uments
    -0.07
    astics
    -0.07
    POSITIVE LOGITS
     with
    0.08
     from
    0.07
    opleft
    0.06
    141
    0.06
    icularly
    0.06
     scene
    0.06
    indre
    0.06
    iculo
    0.06
    with
    0.06
     khá»ıi
    0.06
    Activations Density 0.003%

    No Known Activations