© 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. 61251
    Prev
    Next
    INDEX
    Explanations

    phrases indicating counting or quantifying elements

    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
     Ramp
    -0.07
    oola
    -0.06
     nast
    -0.06
     Bans
    -0.06
    uru
    -0.06
     gran
    -0.06
    ua
    -0.06
    Sense
    -0.06
    ाà¤ĸ
    -0.06
    ìłĢ
    -0.06
    POSITIVE LOGITS
    arters
    0.07
     plenty
    0.07
     enough
    0.07
    érc
    0.07
    atee
    0.07
    å¤ļå°ij
    0.07
     Plenty
    0.07
    igit
    0.07
    /dc
    0.07
    ilt
    0.06
    Activations Density 0.011%

    No Known Activations