© 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. 125419
    Prev
    Next
    INDEX
    Explanations

    references to books or similar literary content

    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
    897
    -0.06
    aries
    -0.06
    cho
    -0.06
    iki
    -0.06
    hydrate
    -0.06
    acemark
    -0.06
    played
    -0.06
    909
    -0.06
    åĭ
    -0.06
    901
    -0.06
    POSITIVE LOGITS
    isay
    0.07
    ourg
    0.07
    erde
    0.07
    iare
    0.07
    uthor
    0.07
    PURE
    0.07
    emiz
    0.07
    æijĺ
    0.07
    xec
    0.07
    ij¸
    0.07
    Activations Density 0.005%

    No Known Activations