INDEX

Explanations

words indicating conditions or situations perceived as unfair or negative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

yat

-0.15

elight

-0.15

Frameworks

-0.14

=\"/

-0.14

rox

-0.14

Ð¼Ñĸ

-0.14

ngr

-0.14

 corres

-0.14

.metamodel

-0.14

 Rolled

-0.14

POSITIVE LOGITS

.fits

0.14

dol

0.14

 Goose

0.14

igu

0.14

 Manhattan

0.14

fon

0.14

_UNUSED

0.14

ì¡´

0.13

 string

0.13

Dol

0.13

Activations Density 0.001%

words indicating conditions or situations perceived as unfair or negative

No Comments

No Known Activations