Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 56239
    Prev
    Next
    INDEX
    Explanations

    contractions and possessives indicating engagement or direction in conversations

    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
    gest
    -0.08
    trie
    -0.07
    fter
    -0.07
    iaux
    -0.07
    oad
    -0.07
    thon
    -0.07
    nze
    -0.07
    ahy
    -0.07
    zell
    -0.07
    iele
    -0.07
    POSITIVE LOGITS
    interp
    0.07
    åĨµ
    0.06
    vern
    0.06
    aran
    0.06
    æĻ´
    0.06
    GO
    0.06
     Gros
    0.06
    enario
    0.06
    down
    0.06
     Ensemble
    0.06
    Activations Density 0.004%

    No Known Activations