© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 61936
    Prev
    Next
    INDEX
    Explanations

    components related to establishing an online presence and brand identity

    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
     ÄĮeská
    -0.07
    esel
    -0.07
    _usec
    -0.07
    ifar
    -0.07
    ùa
    -0.06
    -card
    -0.06
    dia
    -0.06
    èĶµ
    -0.06
    ãĤ¤ãĥī
    -0.06
    gain
    -0.06
    POSITIVE LOGITS
    .AddListener
    0.07
     sire
    0.06
    ael
    0.06
    lem
    0.06
     Masc
    0.06
    æĥ
    0.06
     yola
    0.06
     manned
    0.06
    283
    0.06
    abin
    0.06
    Activations Density 0.001%

    No Known Activations