© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77242
    Prev
    Next
    INDEX
    Explanations

    references to addiction and dependency

    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
    quo
    -0.07
    quam
    -0.07
    que
    -0.07
    ailles
    -0.07
    QUE
    -0.07
     Integrity
    -0.06
    _COMPAT
    -0.06
    ngth
    -0.06
    lobs
    -0.06
    veau
    -0.06
    POSITIVE LOGITS
     habit
    0.07
    ilog
    0.06
    habit
    0.06
     Wes
    0.06
    GEN
    0.06
    -like
    0.06
     hooked
    0.05
    ingly
    0.05
     hab
    0.05
    å¾½
    0.05
    Activations Density 0.010%

    No Known Activations