© 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. 71168
    Prev
    Next
    INDEX
    Explanations

    keywords related to locations and names, particularly in cultural or community 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
    pis
    -0.07
    erland
    -0.07
    ãĤ¢ãĥ¼
    -0.06
    erin
    -0.06
    door
    -0.06
    845
    -0.06
    곡
    -0.06
    er
    -0.06
    ETA
    -0.06
    .synthetic
    -0.06
    POSITIVE LOGITS
    -eyed
    0.08
    ablish
    0.08
    burgh
    0.07
    /javascript
    0.07
    born
    0.07
    eward
    0.07
    CONF
    0.07
    ure
    0.07
    dale
    0.06
    뢰
    0.06
    Activations Density 0.020%

    No Known Activations