© 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. 77010
    Prev
    Next
    INDEX
    Explanations

    words related to change or transformation in various contexts

    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
    ç¢
    -0.07
    vek
    -0.06
    etter
    -0.06
    ÑĢади
    -0.06
    å¢ĥ
    -0.06
     Morr
    -0.06
    licher
    -0.06
    /pp
    -0.06
    rna
    -0.06
    èIJ
    -0.06
    POSITIVE LOGITS
     into
    0.14
    into
    0.11
     Into
    0.10
    Into
    0.09
    stile
    0.09
    _into
    0.09
     INTO
    0.08
     menjadi
    0.08
     become
    0.08
     becomes
    0.08
    Activations Density 0.018%

    No Known Activations