© 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. 18816
    Prev
    Next
    INDEX
    Explanations

    words related to names and locations, particularly in a cultural or artistic context

    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
    ges
    -0.18
    ле
    -0.16
    etty
    -0.16
    де
    -0.16
    ence
    -0.16
    ensive
    -0.16
     bl
    -0.16
    ler
    -0.16
    dings
    -0.15
    135
    -0.15
    POSITIVE LOGITS
    ban
    0.20
    amba
    0.19
    alom
    0.17
    osit
    0.16
    º
    0.15
    villa
    0.15
    alm
    0.15
    ott
    0.15
    ra
    0.15
    ruh
    0.15
    Activations Density 0.004%

    No Known Activations