© 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. 106447
    Prev
    Next
    INDEX
    Explanations

    words or phrases that describe characteristics or qualities of writing

    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
    تÙĪاÙĨ
    -0.07
    jist
    -0.07
    yster
    -0.07
    ellen
    -0.07
    hind
    -0.06
     Kraj
    -0.06
    :".$
    -0.06
    Portal
    -0.06
    alach
    -0.06
     entreprene
    -0.06
    POSITIVE LOGITS
     vital
    0.06
     Fuck
    0.06
    éª
    0.06
    ssf
    0.06
    deo
    0.06
     fucking
    0.06
    ãģĿãģĹãģ¦
    0.06
    ijo
    0.06
    spender
    0.06
     SPDX
    0.06
    Activations Density 0.000%

    No Known Activations