INDEX

Explanations

references to injuries and medical conditions related to sports

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

antis

-0.15

illez

-0.15

è·¡

-0.14

andle

-0.14

æĿĲ

-0.14

èĬ¬

-0.14

uliar

-0.13

pong

-0.13

blink

-0.13

iddi

-0.13

POSITIVE LOGITS

spr

0.43

Spr

0.35

spr

0.32

 injuring

0.30

Spr

0.29

 injured

0.29

 strains

0.29

 torn

0.28

 fracture

0.28

 rupt

0.28

Activations Density 0.066%

references to injuries and medical conditions related to sports

No Comments

No Known Activations