© 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. 27259
    Prev
    Next
    INDEX
    Explanations

    references to blog entries and their associated permalinks

    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
    resher
    -0.07
    hasOne
    -0.07
    anka
    -0.06
    yla
    -0.06
    -0.06
    uch
    -0.06
    136
    -0.06
    WithTitle
    -0.06
    ANTE
    -0.06
     Rape
    -0.05
    POSITIVE LOGITS
    å¿į
    0.07
    igits
    0.07
    çĵ¶
    0.07
    umbnails
    0.07
    rians
    0.07
    .Dictionary
    0.07
    eniz
    0.06
    meni
    0.06
    /comment
    0.06
    ondon
    0.06
    Activations Density 0.002%

    No Known Activations