© 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. 9-LLAMASCOPE-RES-32K
    11. 26809
    Prev
    Next
    INDEX
    Explanations

    terms related to suspicion and confirmation of abuse or neglect

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igham
    -0.20
    gressor
    -0.16
    thora
    -0.15
    ÎijÎł
    -0.14
    :CGRect
    -0.14
    isté
    -0.14
    iday
    -0.14
    inen
    -0.14
    ëĿ½
    -0.14
    icens
    -0.14
    POSITIVE LOGITS
    ably
    0.23
    ively
    0.19
    oot
    0.17
    ance
    0.16
     Moon
    0.15
    ombo
    0.15
     Banc
    0.15
    embr
    0.15
    สà¸ĩ
    0.15
    odi
    0.14
    Activations Density 0.034%

    No Known Activations