© 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. 12-LLAMASCOPE-RES-32K
    6. 14253
    Prev
    Next
    INDEX
    Explanations

    terms related to schizophrenia and related medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iores
    -0.16
    uess
    -0.15
    ient
    -0.14
    pon
    -0.14
    etas
    -0.13
    ummings
    -0.13
    lya
    -0.13
     Shock
    -0.13
    }č↵č↵č↵č↵
    -0.13
    389
    -0.13
    POSITIVE LOGITS
    ANTE
    0.17
    ante
    0.16
    deaux
    0.15
    oger
    0.15
    gia
    0.15
    .Formatter
    0.14
    odont
    0.14
    ger
    0.14
    apor
    0.14
    ulp
    0.14
    Activations Density 0.035%

    No Known Activations