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. 23-LLAMASCOPE-RES-32K
    6. 196
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    must
    -0.27
     must
    -0.26
    å¿ħé¡»
    -0.25
     Must
    -0.25
    Must
    -0.24
     å¿ħ
    -0.23
     gotta
    -0.21
    é¡»
    -0.21
     MUST
    -0.21
    .must
    -0.21
    POSITIVE LOGITS
     should
    0.47
     Should
    0.45
    should
    0.44
    Should
    0.42
    .should
    0.36
    _should
    0.35
    åºĶ该
    0.33
    .Should
    0.32
     deber
    0.31
     SHOULD
    0.31
    Activations Density 0.097%

    No Known Activations