© 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. 24-LLAMASCOPE-RES-32K
    11. 18226
    Prev
    Next
    INDEX
    Explanations

    elements related to validation and correctness, especially in terms of rules and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipop
    -0.14
    à¸²à¸ł
    -0.14
     rarity
    -0.14
    chine
    -0.14
    ëĦ
    -0.13
    lyph
    -0.13
    uns
    -0.13
     ç·¨
    -0.13
    isay
    -0.13
     sam
    -0.13
    POSITIVE LOGITS
     valid
    0.71
    valid
    0.63
     Valid
    0.60
    -valid
    0.58
    Valid
    0.56
     VALID
    0.56
    _valid
    0.53
    .valid
    0.51
     valide
    0.50
     validity
    0.49
    Activations Density 0.144%

    No Known Activations