© 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. 28-LLAMASCOPE-RES-32K
    11. 23309
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives, particularly those denoting size, quality, or emotional tone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idity
    -0.17
     slew
    -0.17
    imo
    -0.15
    rias
    -0.15
    iske
    -0.15
    isu
    -0.15
    ix
    -0.15
     dint
    -0.14
    ouver
    -0.14
    .fromString
    -0.14
    POSITIVE LOGITS
     shame
    0.29
     pity
    0.27
     matter
    0.25
     relief
    0.22
     toss
    0.21
     given
    0.20
     tall
    0.20
     known
    0.19
    given
    0.19
     coincidence
    0.19
    Activations Density 0.184%

    No Known Activations