© 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. 71160
    Prev
    Next
    INDEX
    Explanations

    indications of social or institutional inequalities

    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
    åłĤ
    -0.08
    jab
    -0.08
    uben
    -0.08
    ERVED
    -0.07
    ein
    -0.07
    tru
    -0.07
    üst
    -0.07
    ÑĤож
    -0.07
    uncios
    -0.07
    ymous
    -0.07
    POSITIVE LOGITS
     along
    0.06
    .scalablytyped
    0.06
    ld
    0.06
     altogether
    0.06
    703
    0.06
    LD
    0.06
    senal
    0.06
     depending
    0.06
     LD
    0.06
    along
    0.06
    Activations Density 0.038%

    No Known Activations