© 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. 17-LLAMASCOPE-RES-131K
    11. 57055
    Prev
    Next
    INDEX
    Explanations

    the word "other" and similar conjunctions or alternatives

    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
     unsub
    -0.06
    lac
    -0.06
    on
    -0.06
    ìłĪ
    -0.06
    CAC
    -0.06
     Thrones
    -0.06
    ENCIL
    -0.06
    isko
    -0.05
    PRO
    -0.05
    æ
    -0.05
    POSITIVE LOGITS
    iani
    0.08
    uming
    0.08
    Ĺi
    0.07
    leaf
    0.07
    .scalablytyped
    0.07
    ãĥ«ãĥī
    0.07
    olders
    0.07
    stdarg
    0.07
    ieri
    0.07
     nạn
    0.07
    Activations Density 0.000%

    No Known Activations