© 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. 22-LLAMASCOPE-RES-131K
    11. 4085
    Prev
    Next
    INDEX
    Explanations

    comparative phrases or structures related to evaluation

    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
     Various
    -0.07
    nown
    -0.07
    Various
    -0.07
    buster
    -0.07
    elper
    -0.07
    ifferent
    -0.07
    Certain
    -0.06
    podob
    -0.06
    essen
    -0.06
    uw
    -0.06
    POSITIVE LOGITS
     others
    0.25
    others
    0.20
     Others
    0.20
    Others
    0.18
     ones
    0.14
     دÛĮگراÙĨ
    0.11
    ones
    0.10
     ostatnÃŃ
    0.09
     remaining
    0.09
     rest
    0.08
    Activations Density 0.036%

    No Known Activations