© 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. 30-LLAMASCOPE-RES-32K
    11. 4418
    Prev
    Next
    INDEX
    Explanations

    various references to threats and dangers in social, political, and environmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iao
    -0.21
    artin
    -0.17
    ocker
    -0.15
    Forbidden
    -0.15
    ocket
    -0.15
    quine
    -0.14
    ecided
    -0.14
    Shock
    -0.14
    .pixel
    -0.14
    ctal
    -0.14
    POSITIVE LOGITS
     posed
    0.40
     Pos
    0.29
    posed
    0.25
     pos
    0.23
     facing
    0.22
     faced
    0.22
    ened
    0.22
    ening
    0.22
     pose
    0.22
     assessment
    0.21
    Activations Density 0.042%

    No Known Activations