© 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. 24-LLAMASCOPE-RES-32K
    11. 21264
    Prev
    Next
    INDEX
    Explanations

    specifications and details about battery-powered devices

    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
    bose
    -0.15
     bro
    -0.15
    arius
    -0.15
     amort
    -0.14
     enrich
    -0.14
     Norris
    -0.14
    oron
    -0.14
     dah
    -0.14
    bo
    -0.14
     Boom
    -0.14
    POSITIVE LOGITS
     batteries
    0.40
     Batter
    0.37
     battery
    0.33
     Battery
    0.28
     AAA
    0.28
     alkal
    0.27
    battery
    0.26
    Battery
    0.26
     Lith
    0.25
     lithium
    0.25
    Activations Density 0.024%

    No Known Activations