INDEX

Explanations

instances of the word "a" and other articles or specific context markers in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Ð¸ÑģÑĤÑĢÐ°

-0.17

 Closure

-0.15

verbs

-0.15

opaque

-0.14

Closure

-0.14

geg

-0.14

lÃŃ

-0.14

åĽ´

-0.13

ÑĥÐ¼Ð°

-0.13

åı

-0.13

POSITIVE LOGITS

 interview

0.21

 statement

0.19

 meeting

0.17

 email

0.17

 written

0.16

 recent

0.16

undy

0.16

athom

0.16

 apparent

0.16

 Morr

0.15

Activations Density 0.032%

instances of the word "a" and other articles or specific context markers in statements

No Comments

No Known Activations