© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83214
    Prev
    Next
    INDEX
    Explanations

    comparisons and similarities among various topics or elements

    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
    mart
    -0.07
     Butter
    -0.06
    ladu
    -0.06
    ylon
    -0.06
     chua
    -0.06
    áu
    -0.06
    ока
    -0.06
    umper
    -0.05
     Kimber
    -0.05
    aki
    -0.05
    POSITIVE LOGITS
     except
    0.25
    except
    0.23
     Except
    0.23
    Except
    0.22
     difference
    0.16
     Difference
    0.15
    _except
    0.15
    minus
    0.15
    difference
    0.15
    Difference
    0.14
    Activations Density 0.196%

    No Known Activations