© 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. 24-LLAMASCOPE-RES-32K
    6. 9235
    Prev
    Next
    INDEX
    Explanations

    expressions related to emotional highs and lows or significant peaks in 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
    antor
    -0.16
     Spieler
    -0.15
    ADIUS
    -0.14
    èĺ
    -0.14
    unger
    -0.14
    jar
    -0.13
    getManager
    -0.13
    adius
    -0.13
    linger
    -0.13
    ityEngine
    -0.13
    POSITIVE LOGITS
     peak
    0.90
    peak
    0.72
     Peak
    0.71
     peaks
    0.70
    Peak
    0.69
    _peak
    0.58
     peaked
    0.56
     Peaks
    0.53
     height
    0.48
    å³°
    0.46
    Activations Density 0.129%

    No Known Activations