© 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. 13-LLAMASCOPE-RES-32K
    6. 15586
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and conditions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comb
    -0.16
    hte
    -0.15
    OTAL
    -0.15
    qc
    -0.14
    pedia
    -0.14
     corner
    -0.14
    eldorf
    -0.14
    azon
    -0.14
    297
    -0.13
    ิà¸į
    -0.13
    POSITIVE LOGITS
     reversed
    0.30
     vice
    0.29
     reverse
    0.28
    Reverse
    0.25
     reversal
    0.24
     Vice
    0.24
     Reverse
    0.23
    reverse
    0.23
     inverse
    0.23
     reversing
    0.23
    Activations Density 0.149%

    No Known Activations