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. 96149
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns indicating specific references

    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
    TriState
    -0.09
    ailability
    -0.08
    ÑĥÑĢн
    -0.08
    .optString
    -0.07
    ccb
    -0.07
    atern
    -0.07
    @nate
    -0.07
    xis
    -0.07
    asti
    -0.07
     Mev
    -0.07
    POSITIVE LOGITS
     case
    0.08
    izi
    0.07
     way
    0.07
     cases
    0.06
     ö
    0.06
    erra
    0.06
     do
    0.06
     Unter
    0.06
    goog
    0.05
    lesc
    0.05
    Activations Density 0.024%

    No Known Activations