INDEX

Explanations

negative sentiments or conditions related to health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

wort

-0.15

$MESS

-0.15

AtA

-0.15

 Shades

-0.14

.jet

-0.14

 Ð²Ð¾Ð»

-0.14

vro

-0.14

wa

-0.14

Wal

-0.14

 à¤ľà¤¯

-0.14

POSITIVE LOGITS

 Barrel

0.19

rico

0.17

 barrel

0.15

/bar

0.15

ordion

0.15

eza

0.14

 Ends

0.14

idot

0.14

icot

0.14

uir

0.14

Activations Density 0.000%

negative sentiments or conditions related to health

No Comments

No Known Activations