© 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. 15-LLAMASCOPE-RES-131K
    11. 61888
    Prev
    Next
    INDEX
    Explanations

    references to physical limitations and difficulties

    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
     VÅ¡
    -0.08
    lei
    -0.08
    ól
    -0.07
     anders
    -0.07
     Král
    -0.07
    Å¡ti
    -0.07
    emann
    -0.07
    klä
    -0.07
    obble
    -0.07
    elastic
    -0.07
    POSITIVE LOGITS
    ncmp
    0.07
    å¼ķãģį
    0.06
     Banc
    0.06
    resco
    0.06
     ActionTypes
    0.06
     Booth
    0.05
     Elsa
    0.05
    -envelope
    0.05
    ãĥĸãĥŃ
    0.05
     Brom
    0.05
    Activations Density 0.009%

    No Known Activations