INDEX

Explanations

occurrences of the word "the"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

idor

-0.17

MF

-0.15

Ã©d

-0.15

oren

-0.14

ird

-0.14

deme

-0.14

cyn

-0.14

esh

-0.13

AY

-0.13

POSITIVE LOGITS

aber

0.18

veau

0.18

-toggler

0.15

Vel

0.15

auer

0.14

OLUMNS

0.14

vore

0.13

ÄĽn

0.13

_vp

0.13

<!--[

0.13

Activations Density 0.040%

occurrences of the word "the"

No Comments

No Known Activations