© 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. 15-LLAMASCOPE-RES-131K
    11. 61964
    Prev
    Next
    INDEX
    Explanations

    repetitions of the word 'another' 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
    217
    -0.06
    ensen
    -0.06
     Christian
    -0.06
    atz
    -0.06
     i
    -0.06
    erap
    -0.05
    Christian
    -0.05
     n
    -0.05
     m
    -0.05
    145
    -0.05
    POSITIVE LOGITS
    ding
    0.08
    estone
    0.07
    ountains
    0.07
    ovnÄĽ
    0.07
    gan
    0.07
    /all
    0.07
    egral
    0.07
    another
    0.07
    otte
    0.07
    ildo
    0.07
    Activations Density 0.014%

    No Known Activations