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. 20-LLAMASCOPE-RES-32K
    6. 13246
    Prev
    Next
    INDEX
    Explanations

    sentences containing various forms of the verb "to be" and prepositions indicating relationships between objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chapman
    -0.18
    323
    -0.15
     Rig
    -0.15
    ire
    -0.15
    gt
    -0.15
     coli
    -0.15
    ship
    -0.14
    ských
    -0.14
    cape
    -0.14
    _PROTO
    -0.14
    POSITIVE LOGITS
    acket
    0.17
    nemonic
    0.17
    bow
    0.16
    aat
    0.15
    umbn
    0.15
    âĶĺ
    0.15
    uste
    0.15
    onaut
    0.15
    ÃŃna
    0.15
    udu
    0.14
    Activations Density 0.002%

    No Known Activations