INDEX

Explanations

instances of the word "speak" and its variations, indicating discussions or expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Eta

-0.16

etta

-0.16

vo

-0.15

_tiles

-0.15

_tile

-0.15

ilter

-0.15

iers

-0.15

pt

-0.14

 TILE

-0.14

voj

-0.14

POSITIVE LOGITS

aris

0.18

arry

0.17

 Brand

0.16

tmpl

0.15

Wes

0.15

 tone

0.15

 interp

0.15

éĻ¢

0.15

 Tone

0.15

0.14

Activations Density 0.022%

instances of the word "speak" and its variations, indicating discussions or expressions

No Comments

No Known Activations