© 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. 10949
    Prev
    Next
    INDEX
    Explanations

    elements related to gameplay mechanics and character progression

    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
    phin
    -0.17
    atron
    -0.15
    borg
    -0.15
    opard
    -0.15
    ieber
    -0.14
    tie
    -0.14
    imore
    -0.14
     serialVersionUID
    -0.13
    leans
    -0.13
    /tiny
    -0.13
    POSITIVE LOGITS
     progress
    0.25
     Progress
    0.22
     farm
    0.21
     level
    0.21
     unlocked
    0.20
    level
    0.20
     progressing
    0.20
    é̲
    0.20
     Farm
    0.20
     earn
    0.20
    Activations Density 0.164%

    No Known Activations