Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 18497
    Prev
    Next
    INDEX
    Explanations

    key terms related to inquiries or questions regarding interactions, outcomes, and assessments within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ???
    -0.23
    ))?
    -0.21
    !!!↵
    -0.21
    )?↵
    -0.20
     ??
    -0.19
     !!!
    -0.19
     ***↵
    -0.19
    !!!↵↵
    -0.18
    !!↵
    -0.17
     xxx
    -0.17
    POSITIVE LOGITS
    2
    0.24
    ?=.*
    0.23
    ?}",
    0.23
    7
    0.23
    ?>/
    0.22
    _QMARK
    0.21
    3
    0.19
    9
    0.19
    ?(:
    0.19
    ?;↵↵
    0.19
    Activations Density 0.067%

    No Known Activations