© 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. 305
    Prev
    Next
    INDEX
    Explanations

    phrases that convey possession or existence

    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
     itself
    -0.53
     its
    -0.40
     Its
    -0.35
    Its
    -0.32
    å®ĥ
    -0.28
    its
    -0.25
     оно
    -0.25
     Ñıке
    -0.23
    was
    -0.20
     Ø®ÙĪدش
    -0.20
    POSITIVE LOGITS
     themselves
    0.71
     their
    0.49
    Their
    0.45
     Their
    0.45
    their
    0.44
     thems
    0.35
     leurs
    0.35
     иÑħ
    0.34
     jejich
    0.33
     leur
    0.32
    Activations Density 0.275%

    No Known Activations