INDEX

Explanations

terms associated with regulatory or compliance issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

imar

-0.15

ISTIC

-0.14

mund

-0.14

Īëĭ¤

-0.14

ine

-0.13

aren

-0.13

LOSE

-0.13

akov

-0.13

 Ð¶Ðµ

-0.13

ãĥĸãĥŃ

-0.13

POSITIVE LOGITS

amat

0.15

typeparam

0.15

fy

0.14

QS

0.14

IID

0.14

 Bran

0.14

UIScreen

0.14

uces

0.14

etest

0.14

Activations Density 0.027%

terms associated with regulatory or compliance issues

No Comments

No Known Activations