© 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. 14-LLAMASCOPE-RES-32K
    11. 31601
    Prev
    Next
    INDEX
    Explanations

    negations and conditional phrases indicating refusal or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äl
    -0.16
    ndx
    -0.16
    reet
    -0.16
    zdy
    -0.15
    iên
    -0.15
    rar
    -0.14
    ripp
    -0.14
    iedade
    -0.14
    lew
    -0.14
    ntax
    -0.13
    POSITIVE LOGITS
     be
    0.17
     diá»ħn
    0.16
    iece
    0.16
    åĵ¡
    0.15
    quet
    0.14
    åijĺ
    0.14
     sul
    0.14
    rut
    0.14
    -linear
    0.14
    ogo
    0.14
    Activations Density 0.074%

    No Known Activations