© 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. 24-LLAMASCOPE-RES-32K
    6. 6202
    Prev
    Next
    INDEX
    Explanations

    personal experiences and expressions of emotional struggles

    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
    steder
    -0.15
    orca
    -0.14
    лаÑģÑĤи
    -0.14
    jeme
    -0.14
    DirectoryName
    -0.14
    PLETED
    -0.13
    ujet
    -0.13
    ениÑıми
    -0.13
     received
    -0.13
    quez
    -0.13
    POSITIVE LOGITS
     decided
    0.56
     decide
    0.53
     decides
    0.51
    åĨ³å®ļ
    0.43
     decision
    0.40
     deciding
    0.40
     decid
    0.38
     Decide
    0.36
    決å®ļ
    0.34
    decision
    0.32
    Activations Density 0.399%

    No Known Activations