© 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. 23-LLAMASCOPE-RES-32K
    11. 30367
    Prev
    Next
    INDEX
    Explanations

    references to notable figures, events, or concepts related to history and art

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    paging
    -0.16
    paid
    -0.15
     popis
    -0.15
    _pixels
    -0.15
    maz
    -0.15
    _pixel
    -0.14
     punch
    -0.14
    edis
    -0.14
     hl
    -0.14
    avan
    -0.14
    POSITIVE LOGITS
    (PC
    0.26
     PP
    0.23
    (P
    0.22
     PSP
    0.20
     PC
    0.20
     PL
    0.20
    ÂłPS
    0.20
     PQ
    0.20
    (PR
    0.20
     PW
    0.20
    Activations Density 0.280%

    No Known Activations