INDEX

Explanations

references to geographical locations and biographical details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

shint

-0.14

 genu

-0.14

 frequent

-0.14

annel

-0.13

 cerv

-0.13

alers

-0.13

 room

-0.13

 stol

-0.13

erto

-0.13

optgroup

-0.13

POSITIVE LOGITS

 StringType

0.15

angan

0.15

unk

0.15

uil

0.14

osi

0.14

.dylib

0.14

inke

0.14

ungal

0.14

NCY

0.14

anan

0.14

Activations Density 0.034%

references to geographical locations and biographical details

No Comments

No Known Activations