INDEX

Explanations

phrases discussing justifications or explanations for actions or beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

gow

-0.17

uye

-0.15

/run

-0.15

ÐºÐ°Ñģ

-0.15

ay

-0.14

achi

-0.14

moy

-0.14

uy

-0.14

ipa

-0.14

/read

-0.13

POSITIVE LOGITS

why

0.22

why

0.19

Ã¼stÃ¼

0.18

lessly

0.17

hift

0.17

nement

0.16

APPER

0.16

 dolayÄ±

0.16

afort

0.16

nal

0.16

Activations Density 0.047%

phrases discussing justifications or explanations for actions or beliefs

No Comments

No Known Activations