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. 87478
    Prev
    Next
    INDEX
    Explanations

    phrases related to the absence of evidence or accusations

    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
    ikal
    -0.08
    uliar
    -0.08
    itu
    -0.08
    alars
    -0.08
    ãĥ«ãĤ¯
    -0.07
    tributes
    -0.07
    esters
    -0.07
     actionTypes
    -0.07
    VERTISE
    -0.07
    /tool
    -0.07
    POSITIVE LOGITS
     Alan
    0.06
    505
    0.06
    rot
    0.06
    æĤł
    0.05
    125
    0.05
    rots
    0.05
     BDS
    0.05
    ve
    0.05
    105
    0.05
    нима
    0.05
    Activations Density 0.000%

    No Known Activations