© 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. 843
    Prev
    Next
    INDEX
    Explanations

    numerical data related to rankings or statistics

    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
    alborg
    -0.07
    arhus
    -0.07
    ãĥ³ãĤ¸
    -0.07
    elu
    -0.07
     dequeueReusableCellWithIdentifier
    -0.07
    éo
    -0.06
    ifu
    -0.06
    ennent
    -0.06
     завод
    -0.06
    iami
    -0.06
    POSITIVE LOGITS
    efa
    0.07
    .async
    0.07
    heim
    0.07
    StackNavigator
    0.06
    ĸ
    0.06
     Tip
    0.06
    icz
    0.06
    ators
    0.06
     tip
    0.06
    ä¹ĭä¸Ģ
    0.06
    Activations Density 0.004%

    No Known Activations