© 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. 128513
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantity or prevalence

    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
    ìĹŃ
    -0.07
     spite
    -0.07
    격
    -0.07
    ÄįÃŃ
    -0.07
    ieber
    -0.06
     вдÑĢÑĥг
    -0.06
    asm
    -0.06
    asi
    -0.06
    ere
    -0.06
     Demir
    -0.06
    POSITIVE LOGITS
     cases
    0.14
     case
    0.12
    cases
    0.11
     instance
    0.10
     instances
    0.09
     casos
    0.09
    instances
    0.08
     Cases
    0.08
     caso
    0.08
    case
    0.08
    Activations Density 0.023%

    No Known Activations