© 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. 119440
    Prev
    Next
    INDEX
    Explanations

    themes related to conflict and personal struggle

    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
    LOTS
    -0.08
    fragistics
    -0.08
    cestor
    -0.08
    ManagedObject
    -0.08
    å¯Ĵ
    -0.07
    ocale
    -0.07
    RootElement
    -0.07
    ",__
    -0.07
    оваÑĢ
    -0.07
    lech
    -0.07
    POSITIVE LOGITS
    mma
    0.06
     &
    0.05
     day
    0.05
    zl
    0.05
     loved
    0.05
    :
    0.05
     ï
    0.05
     Supported
    0.05
     their
    0.05
     Minimum
    0.05
    Activations Density 0.007%

    No Known Activations