© 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. 19-LLAMASCOPE-RES-32K
    11. 2275
    Prev
    Next
    INDEX
    Explanations

    references to demographic topics or terms related to identity and social categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vet
    -0.16
    lied
    -0.16
    achs
    -0.16
    iously
    -0.15
    elib
    -0.14
     ogs
    -0.14
    度
    -0.14
    edback
    -0.14
    ificant
    -0.14
    bd
    -0.14
    POSITIVE LOGITS
     dem
    0.23
     Dem
    0.21
    Dem
    0.18
    dem
    0.17
     DEM
    0.17
    urge
    0.16
    meni
    0.15
    214
    0.15
    ographics
    0.15
    stration
    0.15
    Activations Density 0.015%

    No Known Activations