INDEX

Explanations

comparisons to other entities or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

oku

-0.16

ngen

-0.14

ibri

-0.14

ãĥ³ãĤ¸

-0.14

ÑģÑĤÐ¾ÑĢ

-0.14

meden

-0.14

ÑĨÑİ

-0.14

bose

-0.13

 Stern

-0.13

ĵåĲį

-0.13

POSITIVE LOGITS

aits

0.17

 Hooks

0.16

Prev

0.15

ÐµÐ»Ñı

0.15

 ReturnType

0.15

imon

0.15

ower

0.14

amik

0.14

tl

0.14

 hood

0.14

Activations Density 0.174%

comparisons to other entities or items

No Comments

No Known Activations