© 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. 26-LLAMASCOPE-RES-32K
    11. 6998
    Prev
    Next
    INDEX
    Explanations

    themes of jealousy and comparisons between individuals in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OnInit
    -0.14
    ilver
    -0.14
    é«
    -0.14
    orca
    -0.14
    å¥ij
    -0.13
    AndWait
    -0.13
    æķ¦
    -0.13
    onnen
    -0.13
    regor
    -0.13
    Ñİк
    -0.13
    POSITIVE LOGITS
     Je
    0.68
     je
    0.68
     jealous
    0.65
    je
    0.63
    Je
    0.63
     jealousy
    0.61
    Âłje
    0.60
     JE
    0.55
     env
    0.53
    JE
    0.52
    Activations Density 0.122%

    No Known Activations