INDEX

Explanations

variations of the word "beg" and its related forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

eres

-0.18

rophe

-0.17

llib

-0.16

imuth

-0.16

ifers

-0.16

oze

-0.15

riors

-0.15

eriod

-0.15

ifer

-0.15

eries

-0.14

POSITIVE LOGITS

gar

0.26

gars

0.23

ging

0.20

otten

0.20

gs

0.20

gin

0.19

Beg

0.18

beg

0.18

ears

0.17

gers

0.17

Activations Density 0.006%

variations of the word "beg" and its related forms

No Comments

No Known Activations