© 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. 25-LLAMASCOPE-RES-32K
    11. 22489
    Prev
    Next
    INDEX
    Explanations

    actions related to taking, such as taking photos, walks, or meals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jam
    -0.15
     Taken
    -0.14
    anch
    -0.14
    anc
    -0.14
     çī
    -0.14
    .Task
    -0.14
    prs
    -0.13
    Bid
    -0.13
    arden
    -0.13
     seasons
    -0.13
    POSITIVE LOGITS
     advantage
    0.26
     Advantage
    0.20
     shelter
    0.19
     refuge
    0.18
     det
    0.18
     spin
    0.18
     advant
    0.17
    ä¼ĺåĬ¿
    0.17
     Shelter
    0.16
    kaar
    0.16
    Activations Density 0.053%

    No Known Activations