© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 105511
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to mathematical consistency and disappearance of values in calculations

    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
    vel
    -0.07
    anzi
    -0.06
    akes
    -0.06
    comb
    -0.06
    mutation
    -0.06
    ein
    -0.06
    uben
    -0.06
    _variable
    -0.06
    asser
    -0.06
    _pieces
    -0.06
    POSITIVE LOGITS
     unless
    0.07
     except
    0.07
    ussy
    0.07
    koa
    0.07
    iked
    0.06
     everywhere
    0.06
    except
    0.06
    voy
    0.06
    apus
    0.06
    ent
    0.06
    Activations Density 0.110%

    No Known Activations