INDEX

Explanations

phrases indicating steps, processes, or actions that require proper handling or planning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

idth

-0.17

_UD

-0.16

uling

-0.15

opher

-0.15

ought

-0.15

Ã¡la

-0.15

eken

-0.15

PU

-0.15

otherapy

-0.15

renom

-0.14

POSITIVE LOGITS

 advantage

0.29

 cues

0.20

 seriously

0.19

 liberties

0.19

 pride

0.19

 ÑĥÑĩÐ°ÑģÑĤÑĮ

0.19

 steps

0.18

ijk

0.18

cue

0.18

adv

0.18

Activations Density 0.091%

phrases indicating steps, processes, or actions that require proper handling or planning

No Comments

No Known Activations