© 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. 15-LLAMASCOPE-RES-131K
    11. 27315
    Prev
    Next
    INDEX
    Explanations

    expressions related to giving and amplifying voices

    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
    DECL
    -0.09
    ilig
    -0.08
    ubber
    -0.08
    TestingModule
    -0.07
    款
    -0.07
    fad
    -0.07
    _DL
    -0.07
    tÄĽÅ¾
    -0.06
     Verfüg
    -0.06
    -runtime
    -0.06
    POSITIVE LOGITS
     voices
    0.08
    rieve
    0.07
     representation
    0.06
    HZ
    0.06
     Representation
    0.06
    InputLabel
    0.06
     extrem
    0.06
    å§ĵ
    0.06
     proverb
    0.06
    representation
    0.06
    Activations Density 0.013%

    No Known Activations