© 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. 30-LLAMASCOPE-RES-32K
    11. 22123
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Angela" and related terms, particularly in contexts that evoke strong emotional responses or themes of anger

    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
    ksen
    -0.18
    podob
    -0.16
    etat
    -0.15
    ouser
    -0.15
    æ½
    -0.15
    etto
    -0.15
    atives
    -0.15
    ahun
    -0.15
    acles
    -0.15
    etten
    -0.15
    POSITIVE LOGITS
    uish
    0.26
    ered
    0.24
    lic
    0.23
    strom
    0.21
    kor
    0.21
    gota
    0.21
    olan
    0.20
    iolet
    0.20
    leton
    0.20
    ry
    0.20
    Activations Density 0.008%

    No Known Activations