© 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. 10-LLAMASCOPE-RES-32K
    11. 30412
    Prev
    Next
    INDEX
    Explanations

    components and functions related to UI helpers and data processing in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Commerce
    -0.15
     Journal
    -0.15
    abling
    -0.14
     journal
    -0.14
     lev
    -0.14
     вд
    -0.14
     supervision
    -0.14
    enza
    -0.13
    abaj
    -0.13
     receipts
    -0.13
    POSITIVE LOGITS
    ktop
    0.19
    tual
    0.16
    vetica
    0.16
    ãĤ«ãĥ¼
    0.14
    _mE
    0.14
    ropa
    0.14
    ongs
    0.14
    ìĬ¤ì½Ķ
    0.14
    .blob
    0.14
    onian
    0.14
    Activations Density 0.160%

    No Known Activations