© 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. 129026
    Prev
    Next
    INDEX
    Explanations

    references to mobile health applications and wearable devices in clinical studies

    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
     even
    -0.06
     something
    -0.06
    untu
    -0.06
    arter
    -0.06
     —
    -0.06
    even
    -0.06
    r
    -0.06
    [^
    -0.06
    rary
    -0.06
     subclasses
    -0.05
    POSITIVE LOGITS
    SharedPointer
    0.08
    icontrol
    0.07
    ãĢ
    0.07
    ัวร
    0.07
    TexCoord
    0.07
    _dur
    0.07
    .bunifuFlatButton
    0.07
    }elseif
    0.07
    OTAL
    0.06
    daf
    0.06
    Activations Density 0.036%

    No Known Activations