© 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. 57154
    Prev
    Next
    INDEX
    Explanations

    instances of specific classifications and relationships between entities

    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
    iba
    -0.07
    .MixedReality
    -0.07
    èĥ¶
    -0.07
    GMT
    -0.07
    wright
    -0.06
    vise
    -0.06
    .crm
    -0.06
    _INFORMATION
    -0.06
     verv
    -0.06
    icorn
    -0.06
    POSITIVE LOGITS
     given
    0.11
     particular
    0.09
    given
    0.08
     particul
    0.07
     specific
    0.07
    _given
    0.07
     Given
    0.06
    iper
    0.06
    Given
    0.06
     ISBN
    0.05
    Activations Density 0.060%

    No Known Activations