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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95981
    Prev
    Next
    INDEX
    Explanations

    references to positive and negative financial outcomes or risks

    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
    ew
    -0.07
    .cwd
    -0.07
    AttributeValue
    -0.07
    zin
    -0.07
    appa
    -0.07
     sqlCommand
    -0.06
    odos
    -0.06
    sWith
    -0.06
    ãĥ«ãĤ¯
    -0.06
    avana
    -0.06
    POSITIVE LOGITS
    querque
    0.07
    IMUM
    0.07
    arily
    0.06
    738
    0.06
    /down
    0.06
     Becker
    0.06
    imary
    0.06
     Dive
    0.06
    .rnn
    0.06
    GINE
    0.06
    Activations Density 0.002%

    No Known Activations