© 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. 30-LLAMASCOPE-RES-32K
    11. 21165
    Prev
    Next
    INDEX
    Explanations

    technical terms and status updates related to equipment and facilities

    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
    indi
    -0.17
    enco
    -0.17
    .SDK
    -0.15
    à¤Ľ
    -0.15
    edom
    -0.14
     migrationBuilder
    -0.13
    _frm
    -0.13
    ÙĪسÛĮ
    -0.13
    vem
    -0.12
    -FIRST
    -0.12
    POSITIVE LOGITS
     operational
    0.61
     active
    0.56
     functional
    0.53
    active
    0.45
     operative
    0.45
     Operational
    0.44
     functioning
    0.43
     ACTIVE
    0.41
    functional
    0.41
     working
    0.41
    Activations Density 0.313%

    No Known Activations