© 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. 60825
    Prev
    Next
    INDEX
    Explanations

    the preposition "at" used in various 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
    hist
    -0.06
    our
    -0.06
    ÅĽcie
    -0.06
    airro
    -0.06
    ala
    -0.05
    oun
    -0.05
    pare
    -0.05
    isma
    -0.05
    alm
    -0.05
    orman
    -0.05
    POSITIVE LOGITS
    ysz
    0.08
    еÑĢин
    0.07
     nutshell
    0.07
    gons
    0.07
    evi
    0.07
    gages
    0.07
    olik
    0.07
    CodeAt
    0.07
     Verfügung
    0.07
    vfs
    0.07
    Activations Density 0.032%

    No Known Activations