© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3779
    Prev
    Next
    INDEX
    Explanations

    negative qualifiers that suggest something is less important or optional

    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
    ud
    -0.06
    ip
    -0.06
    dr
    -0.06
    ans
    -0.06
    vol
    -0.06
     also
    -0.06
     sparing
    -0.06
    orrow
    -0.06
    in
    -0.06
    okin
    -0.06
    POSITIVE LOGITS
    alion
    0.09
    phalt
    0.09
    ضر
    0.08
    istrovstvÃŃ
    0.07
    ฤษ
    0.07
    ç¹Ķ
    0.07
    ìĬ¤íĦ°
    0.07
    rve
    0.07
    OUCH
    0.07
    .AWS
    0.07
    Activations Density 0.028%

    No Known Activations