© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106826
    Prev
    Next
    INDEX
    Explanations

    expressions of being a fan or supporter of various subjects

    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
    auc
    -0.07
    phere
    -0.07
    ulk
    -0.07
    iya
    -0.07
    okie
    -0.07
    èĪĪ
    -0.07
    Commerce
    -0.07
    edes
    -0.07
    deo
    -0.07
    owell
    -0.06
    POSITIVE LOGITS
    atical
    0.07
    ernal
    0.06
    boy
    0.06
    >Status
    0.06
    ãĥ³ãĥĨ
    0.06
    atically
    0.06
    atic
    0.06
    ResultSet
    0.06
    eye
    0.06
    atics
    0.06
    Activations Density 0.006%

    No Known Activations