© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 128973
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or criticisms related to various topics

    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
    s
    -0.13
    a
    -0.10
    z
    -0.09
     latter
    -0.09
    Ùĩ
    -0.09
    n
    -0.09
    h
    -0.09
    m
    -0.08
    d
    -0.08
    olume
    -0.08
    POSITIVE LOGITS
    /-
    0.10
    ħn
    0.07
    ık
    0.07
    ADOR
    0.07
    rası
    0.07
     Bris
    0.07
    rador
    0.07
    ÑįÑĤомÑĥ
    0.07
    ador
    0.06
    edBy
    0.06
    Activations Density 0.101%

    No Known Activations