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. 75051
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    mailer
    -0.07
    ardon
    -0.07
     equipments
    -0.07
    ¶Į
    -0.07
    .decorate
    -0.06
    िह
    -0.06
    æĪı
    -0.06
    ego
    -0.06
     («
    -0.06
    .synthetic
    -0.06
    POSITIVE LOGITS
    uki
    0.07
    ymi
    0.06
    OKIE
    0.06
    adopt
    0.06
    Ñĥ
    0.06
     Ki
    0.06
    primitive
    0.06
     Bee
    0.05
     Its
    0.05
     Roose
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.