© 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. 40831
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" in various forms

    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
    .scalablytyped
    -0.08
    нил
    -0.08
    stab
    -0.08
    SION
    -0.08
    abra
    -0.07
    ":[{↵
    -0.07
    issant
    -0.07
    anzeigen
    -0.07
    μιÏĥ
    -0.07
     prob
    -0.07
    POSITIVE LOGITS
     the
    0.07
    ertype
    0.06
     Cos
    0.06
    _identity
    0.06
    zte
    0.06
    etus
    0.06
    eras
    0.06
    asher
    0.05
    stddef
    0.05
     cosm
    0.05
    Activations Density 0.010%

    No Known Activations