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. 26-LLAMASCOPE-RES-32K
    6. 1429
    Prev
    Next
    INDEX
    Explanations

    references to the brand "Bell" and its associated products or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ette
    -0.19
    ÑĮÑİ
    -0.17
    elder
    -0.16
    adlo
    -0.16
    etten
    -0.15
    esus
    -0.15
    ãģįãģŁ
    -0.15
    esty
    -0.15
    essional
    -0.15
    yor
    -0.15
    POSITIVE LOGITS
    amy
    0.30
    ows
    0.29
    AMY
    0.25
    atrix
    0.23
    flower
    0.22
    hop
    0.22
    inz
    0.22
    inger
    0.20
    Bell
    0.20
     Bell
    0.20
    Activations Density 0.011%

    No Known Activations