© 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. 78580
    Prev
    Next
    INDEX
    Explanations

    themes related to societal issues and personal narratives

    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
     country
    -0.07
    COND
    -0.06
    country
    -0.06
    istrovstvÃŃ
    -0.06
    ho
    -0.06
    ολ
    -0.06
    .spy
    -0.06
     Perf
    -0.06
    _customize
    -0.05
    ifestyles
    -0.05
    POSITIVE LOGITS
    å¿Ĺ
    0.07
     branching
    0.07
    ÑĢог
    0.07
    बल
    0.06
    landa
    0.06
    (&$
    0.06
    enger
    0.06
     OnCollision
    0.06
    اراÙĨ
    0.06
    emet
    0.06
    Activations Density 0.001%

    No Known Activations