© 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. 23-LLAMASCOPE-RES-32K
    11. 15867
    Prev
    Next
    INDEX
    Explanations

    expressions of acknowledgment and support for initiatives or policies

    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
    vier
    -0.14
     keÅŁ
    -0.13
    oref
    -0.13
    nem
    -0.12
     rou
    -0.12
    Scenario
    -0.12
    masında
    -0.12
    iens
    -0.12
     erst
    -0.12
    ayscale
    -0.12
    POSITIVE LOGITS
     attempts
    0.68
     attempt
    0.67
     effort
    0.65
     efforts
    0.64
     Attempts
    0.59
     Attempt
    0.59
    attempt
    0.57
    Attempt
    0.54
    Attempts
    0.51
     attempting
    0.50
    Activations Density 0.004%

    No Known Activations