INDEX

Explanations

terms related to concussions and head injuries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 okol

-0.13

ëĿ½

-0.12

_plural

-0.11

Ð¼ÐµÑĩ

-0.11

../../../

-0.11

lÃ¡d

-0.11

Ð´Ð°ÐµÑĤ

-0.11

lessly

-0.10

OME

-0.10

uforia

-0.10

POSITIVE LOGITS

ternet

0.14

âĢ¦↵↵↵

0.14

preneur

0.13

paque

0.13

updatedAt

0.12

wright

0.12

 proper

0.12

 Proper

0.12

 ÂŃ

0.11

ddf

0.11

Activations Density 3.286%

terms related to concussions and head injuries

No Comments

No Known Activations