INDEX

Explanations

elements related to medals and awards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 baskets

-0.17

ehler

-0.15

 Chairs

-0.15

raham

-0.15

Ð¾Ð»Ð¾Ñģ

-0.14

yonel

-0.14

asley

-0.14

aeper

-0.14

rary

-0.14

obox

-0.14

POSITIVE LOGITS

Bad

0.40

_bad

0.37

BAD

0.36

 badges

0.35

bad

0.35

 badge

0.35

 insign

0.35

bad

0.34

Bad

0.34

BAD

0.34

Activations Density 0.073%

elements related to medals and awards

No Comments

No Known Activations