© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 18369
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to meteorology and radar systems

    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
     sv
    -0.15
    gth
    -0.15
     sac
    -0.14
    leme
    -0.14
    ÑĢел
    -0.14
    moz
    -0.14
     sacr
    -0.14
    itemap
    -0.14
     Seeder
    -0.14
    rello
    -0.14
    POSITIVE LOGITS
     Normal
    0.18
    ub
    0.17
     recom
    0.16
     normal
    0.16
    Normal
    0.16
    μιÏĥ
    0.16
     Palm
    0.16
    ORMAL
    0.15
     NORMAL
    0.15
    MI
    0.15
    Activations Density 0.040%

    No Known Activations