INDEX

Explanations

phrases related to presence, participation, or involvement in an activity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

IQ

-0.15

 Bryant

-0.15

Ń

-0.14

uer

-0.14

YA

-0.14

lech

-0.14

idos

-0.13

erte

-0.13

Tro

-0.13

 prov

-0.13

POSITIVE LOGITS

 nháº±m

0.21

 ÑĩÑĤÐ¾Ð±Ñĭ

0.20

because

0.19

 because

0.19

 Äĳá»ĥ

0.18

 sole

0.18

ÑĢÐ°Ð´Ð¸

0.18

 inorder

0.17

prim

0.17

 omdat

0.17

Activations Density 0.153%

phrases related to presence, participation, or involvement in an activity

No Comments

No Known Activations