© 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. 30-LLAMASCOPE-RES-32K
    6. 22957
    Prev
    Next
    INDEX
    Explanations

    references to monsters and mythical creatures

    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
    ovit
    -0.17
    оÑĢов
    -0.17
    rabbit
    -0.16
     rabbit
    -0.15
     Artem
    -0.15
     rabbits
    -0.15
    ocator
    -0.14
    buz
    -0.14
    çĽĹ
    -0.14
     Nut
    -0.14
    POSITIVE LOGITS
     Godzilla
    0.38
     Kai
    0.29
     Kong
    0.28
    God
    0.28
     GOD
    0.28
     Monster
    0.26
     monsters
    0.25
     God
    0.25
     King
    0.25
     monster
    0.25
    Activations Density 0.010%

    No Known Activations