© 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. 78772
    Prev
    Next
    INDEX
    Explanations

    citation details, particularly pertaining to academic references

    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
    Loaded
    -0.06
     Trades
    -0.06
     Dann
    -0.05
     Garr
    -0.05
     Printable
    -0.05
     Goth
    -0.05
     cut
    -0.05
    _PY
    -0.05
    çĤī
    -0.05
     Loaded
    -0.05
    POSITIVE LOGITS
    zo
    0.07
    bourg
    0.07
     baiser
    0.07
    UFF
    0.07
    organic
    0.07
    pub
    0.07
    aker
    0.06
    UDA
    0.06
    olecular
    0.06
    viron
    0.06
    Activations Density 0.007%

    No Known Activations