© 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. 21-LLAMASCOPE-RES-32K
    11. 10044
    Prev
    Next
    INDEX
    Explanations

    instances of words related to horror with an emphasis on adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oretical
    -0.30
    orem
    -0.29
    oret
    -0.28
    adecimal
    -0.26
    gunakan
    -0.26
    selling
    -0.25
    pects
    -0.25
    give
    -0.25
    ories
    -0.24
    linear
    -0.23
    POSITIVE LOGITS
    achusetts
    0.26
    jamin
    0.24
    adays
    0.23
    odore
    0.23
    gerald
    0.23
    efeller
    0.23
    lahoma
    0.22
    greSQL
    0.22
    akhstan
    0.22
    rador
    0.22
    Activations Density 0.378%

    No Known Activations