© 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. 22-LLAMASCOPE-RES-131K
    6. 4172
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'f' 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
    l
    -0.08
    ITO
    -0.08
    ace
    -0.07
    ox
    -0.07
    r
    -0.07
    ت
    -0.07
    оÑĢ
    -0.07
    ile
    -0.07
    ore
    -0.07
    la
    -0.07
    POSITIVE LOGITS
    y
    0.10
    ords
    0.09
    hire
    0.08
    uegos
    0.07
    ording
    0.07
    Ĺi
    0.07
    uchs
    0.07
    ieber
    0.07
    adden
    0.07
    yg
    0.07
    Activations Density 0.019%

    No Known Activations