© 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. 17-LLAMASCOPE-RES-131K
    11. 61119
    Prev
    Next
    INDEX
    Explanations

    elements related to media content identifiers, such as links or file formats

    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
    ming
    -0.07
    pty
    -0.06
    ussia
    -0.06
    zeit
    -0.06
    isAdmin
    -0.06
    icing
    -0.06
    izard
    -0.06
    ùa
    -0.06
    pees
    -0.06
    Ñĥж
    -0.06
    POSITIVE LOGITS
    #ab
    0.07
    #ac
    0.07
    0.07
    uble
    0.06
    ↵
    0.06
    íĬ
    0.06
    \OptionsResolver
    0.06
    sav
    0.06
    μι
    0.06
    íĦ
    0.06
    Activations Density 0.002%

    No Known Activations