© 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. 15-LLAMASCOPE-RES-32K
    11. 9621
    Prev
    Next
    INDEX
    Explanations

    terms related to authorship and credit ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fold
    -0.16
    986
    -0.15
     fold
    -0.14
     folded
    -0.14
    atalog
    -0.14
    odef
    -0.14
     folding
    -0.14
    ãĥ³ãĥĨãĤ£
    -0.14
    compatible
    -0.14
    _MATCH
    -0.14
    POSITIVE LOGITS
     credit
    0.31
     credits
    0.28
     Credit
    0.25
    credits
    0.24
     attribution
    0.24
     credited
    0.22
     créd
    0.22
     acknowledgement
    0.21
     acknowled
    0.21
     attrib
    0.21
    Activations Density 0.177%

    No Known Activations