Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84285
    Prev
    Next
    INDEX
    Explanations

    words related to aggression and contentious behavior

    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
    elter
    -0.06
    aras
    -0.06
     rang
    -0.06
     stub
    -0.06
     Ethnic
    -0.05
    opoulos
    -0.05
     riv
    -0.05
    âĢĤ
    -0.05
     Tough
    -0.05
     Fay
    -0.05
    POSITIVE LOGITS
    åĿĬ
    0.08
     çĥ
    0.08
     {{--<
    0.07
    ieber
    0.07
    ">//
    0.07
    vetica
    0.07
     trop
    0.07
    SingleNode
    0.07
    ternet
    0.07
    ãĥ«ãĤ¯
    0.07
    Activations Density 0.000%

    No Known Activations