© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60692
    Prev
    Next
    INDEX
    Explanations

    instances of movement or change in direction, particularly related to narratives

    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
    ader
    -0.07
    obia
    -0.06
     Lion
    -0.06
    759
    -0.06
    ADED
    -0.06
    elor
    -0.06
     Shelf
    -0.06
     fronts
    -0.06
    boa
    -0.06
     Shen
    -0.06
    POSITIVE LOGITS
     accepted
    0.09
     dev
    0.08
     norms
    0.08
    .dev
    0.08
    accepted
    0.08
     strict
    0.07
     ÑĥÑģÑĤановлен
    0.07
     established
    0.07
     course
    0.07
    Accepted
    0.07
    Activations Density 0.032%

    No Known Activations