© 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. 40830
    Prev
    Next
    INDEX
    Explanations

    specific phrases or expressions that denote arguments or claims

    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
    fon
    -0.08
    lear
    -0.07
    aho
    -0.07
    iets
    -0.06
     disregard
    -0.06
    aleza
    -0.06
    üst
    -0.06
    quier
    -0.06
    è³Ģ
    -0.06
    WISE
    -0.06
    POSITIVE LOGITS
     against
    0.10
    against
    0.09
     arguments
    0.08
     argument
    0.08
    Against
    0.08
     Arguments
    0.08
     Against
    0.08
    ative
    0.08
     made
    0.07
    Arguments
    0.07
    Activations Density 0.012%

    No Known Activations