© 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 EvalsExportsinterp-engineNEWAPI 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. 107915
    Prev
    Next
    INDEX
    Explanations

    phrases related to individualized support or tutoring arrangements

    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
    oen
    -0.10
    lok
    -0.09
    ñana
    -0.08
    nt
    -0.08
    afia
    -0.08
    ACHER
    -0.08
    erli
    -0.08
    etik
    -0.08
    ÙĨÛĮ
    -0.08
    atik
    -0.08
    POSITIVE LOGITS
    /single
    0.08
    /group
    0.08
    iron
    0.07
    /small
    0.07
     Franco
    0.06
    imap
    0.06
    /team
    0.06
     relationship
    0.06
     aspect
    0.06
    nels
    0.06
    Activations Density 0.003%

    No Known Activations