© 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. 4-LLAMASCOPE-RES-32K
    11. 14370
    Prev
    Next
    INDEX
    Explanations

    conditional statements in programming logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    иÑĩа
    -0.15
    /XMLSchema
    -0.15
    andelier
    -0.14
    iller
    -0.14
    æķ·
    -0.14
    .hr
    -0.14
    ervo
    -0.14
    mailer
    -0.14
    elay
    -0.13
    seau
    -0.13
    POSITIVE LOGITS
    XA
    0.17
    anza
    0.16
    istrovstvÃŃ
    0.15
    Du
    0.15
    _oid
    0.14
    wards
    0.14
    нак
    0.14
    vary
    0.14
    ADATA
    0.13
    CustomAttributes
    0.13
    Activations Density 0.021%

    No Known Activations