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. 5-LLAMASCOPE-RES-131K
    6. 126343
    Prev
    Next
    INDEX
    Explanations

    possessive forms of nouns

    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
    æĮ¯ãĤĬ
    -0.07
    argas
    -0.07
    les
    -0.06
    elle
    -0.06
    elles
    -0.06
    -
    -0.06
     Worth
    -0.06
    retry
    -0.06
    ánd
    -0.06
    amed
    -0.06
    POSITIVE LOGITS
    PILE
    0.07
    -Sah
    0.07
    IVERY
    0.07
    é¡»
    0.07
    FRING
    0.06
    NOWLED
    0.06
    à¸´à¸Ľ
    0.06
    _FUNCTIONS
    0.06
    /Instruction
    0.06
    BackStack
    0.06
    Activations Density 0.047%

    No Known Activations