INDEX

Explanations

sequences involving the word "followed" indicating a sequence or progression in events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-0.14

/do

-0.14

rts

-0.13

 terminal

-0.13

Ø²ÙĪ

-0.13

uai

-0.13

ities

-0.13

abel

-0.13

 isize

-0.13

POSITIVE LOGITS

ÑĢÐ¸Ð¼

0.17

 gamb

0.14

ingly

0.14

lient

0.14

Î®Î½

0.14

POW

0.13

 correl

0.13

porte

0.13

 followed

0.13

xz

0.13

Activations Density 0.022%

sequences involving the word "followed" indicating a sequence or progression in events

No Comments

No Known Activations