© 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. 106045
    Prev
    Next
    INDEX
    Explanations

    sentences and phrases related to the consequences of spam or unwanted emails

    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
     Trouble
    -0.06
    ount
    -0.06
     Cont
    -0.06
    anca
    -0.06
    roll
    -0.05
    ãĥ¼ãĥĦ
    -0.05
     roll
    -0.05
    swire
    -0.05
    /Instruction
    -0.05
    -runtime
    -0.05
    POSITIVE LOGITS
     worse
    0.10
     therefore
    0.09
     Worse
    0.09
    egasus
    0.09
    arnation
    0.08
    Therefore
    0.08
    abbo
    0.07
     Therefore
    0.07
    reau
    0.07
    é£İéĻ©
    0.07
    Activations Density 0.074%

    No Known Activations