© 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. 12479
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases indicating a lack of clarity or reference in a narrative context

    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
    uke
    -0.15
    edik
    -0.15
     participant
    -0.13
    arella
    -0.13
    esktop
    -0.13
    erial
    -0.13
    .chapter
    -0.13
     Chapters
    -0.13
    Participant
    -0.13
    ÏĥÏĥ
    -0.13
    POSITIVE LOGITS
     source
    0.63
     sources
    0.55
    source
    0.53
     reason
    0.49
     Source
    0.49
    sources
    0.47
     reasons
    0.46
     SOURCE
    0.46
    -source
    0.45
     Sources
    0.45
    Activations Density 0.045%

    No Known Activations