© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 11397
    Prev
    Next
    INDEX
    Explanations

    concepts related to predictions and forecasting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hart
    -0.17
    ynet
    -0.17
    ê²
    -0.15
    kom
    -0.15
    ész
    -0.14
    kel
    -0.14
    ÅĦ
    -0.14
    ENCHMARK
    -0.14
    ierz
    -0.14
    bidden
    -0.14
    POSITIVE LOGITS
    ably
    0.31
    ions
    0.26
    ively
    0.24
    ive
    0.24
    ors
    0.23
     accuracy
    0.22
    ability
    0.22
     imminent
    0.21
    /pre
    0.20
     based
    0.20
    Activations Density 0.033%

    No Known Activations