© 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. 23-LLAMASCOPE-RES-32K
    11. 21370
    Prev
    Next
    INDEX
    Explanations

    terms related to risk management and mitigation strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨ
    -0.14
    ÙĥÙĦ
    -0.14
    yen
    -0.13
    maal
    -0.13
    undles
    -0.13
    ockey
    -0.13
    /use
    -0.13
    EEE
    -0.13
    _datos
    -0.13
    ##_
    -0.12
    POSITIVE LOGITS
    /mit
    0.29
     potential
    0.25
     possible
    0.24
     effects
    0.20
    /manage
    0.20
    TEGER
    0.19
     Effects
    0.19
    effects
    0.19
     potentially
    0.18
     situations
    0.18
    Activations Density 0.229%

    No Known Activations