© 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. 129199
    Prev
    Next
    INDEX
    Explanations

    references to local community and personal relationships

    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
    nite
    -0.07
    âte
    -0.06
     sy
    -0.06
    ÅĽcie
    -0.06
    _PRIVATE
    -0.06
    ocking
    -0.06
    conde
    -0.06
    IOD
    -0.06
    yte
    -0.05
     Casc
    -0.05
    POSITIVE LOGITS
     neighbour
    0.15
     neighbor
    0.14
     neighborhood
    0.14
    neighbor
    0.13
     neighbours
    0.13
     neighbors
    0.13
     neighbourhood
    0.13
     neighb
    0.11
    neighbors
    0.11
     neigh
    0.11
    Activations Density 0.076%

    No Known Activations