Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 22511
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pass" in various forms and contexts

    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
    lify
    -0.21
    tero
    -0.20
    eyi
    -0.19
    ean
    -0.17
    ead
    -0.17
    ting
    -0.17
    tings
    -0.16
    ty
    -0.16
    ey
    -0.15
    ted
    -0.15
    POSITIVE LOGITS
    ive
    0.26
    engers
    0.26
    ionate
    0.25
    enger
    0.24
    ported
    0.24
    ione
    0.23
    code
    0.22
    ages
    0.21
    arella
    0.21
    IVE
    0.21
    Activations Density 0.008%

    No Known Activations