© 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. 74881
    Prev
    Next
    INDEX
    Explanations

    measurements and their units

    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
    ushi
    -0.08
    isti
    -0.07
    afs
    -0.07
    .pb
    -0.07
    ãĥ³ãĤ°
    -0.07
    ä¸ĺ
    -0.07
    arshal
    -0.07
    gran
    -0.07
     Ramp
    -0.06
     ãĢ
    -0.06
    POSITIVE LOGITS
    eras
    0.06
    akan
    0.06
     rain
    0.06
    K
    0.06
    up
    0.06
    fon
    0.06
    im
    0.05
    rain
    0.05
    apan
    0.05
    yle
    0.05
    Activations Density 0.000%

    No Known Activations