© 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. 78612
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating negative reception or criticism towards media content

    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
    https
    -0.07
    â
    -0.07
    munition
    -0.07
    ACA
    -0.07
    orges
    -0.07
    ersions
    -0.07
    ðŁĴ
    -0.07
    ðŁ
    -0.07
    ðŁĺ
    -0.07
     selfie
    -0.07
    POSITIVE LOGITS
    boru
    0.07
    ahn
    0.07
     Düz
    0.07
    inspace
    0.06
     Borders
    0.06
    anova
    0.06
    ãģ°ãģĭãĤĬ
    0.06
    宾
    0.06
     brainstorm
    0.06
    éĺµ
    0.06
    Activations Density 0.000%

    No Known Activations