© 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. 126014
    Prev
    Next
    INDEX
    Explanations

    terms related to conditions and assessments of adequacy or suitability

    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
    except
    -0.07
     except
    -0.07
    ENS
    -0.07
    vrier
    -0.07
    ÃŁer
    -0.06
     Except
    -0.06
    bled
    -0.06
    ses
    -0.06
    ¯¯¯¯
    -0.06
    bles
    -0.06
    POSITIVE LOGITS
     based
    0.09
     Based
    0.07
    based
    0.07
     according
    0.07
    Based
    0.07
     Echo
    0.06
    ाण
    0.06
     dá»±a
    0.06
    gnore
    0.06
     given
    0.06
    Activations Density 0.025%

    No Known Activations