INDEX

Explanations

terms related to folding and mold

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

TY

-0.18

ifax

-0.15

imals

-0.15

efa

-0.15

 folds

-0.15

anning

-0.15

ESS

-0.14

itation

-0.14

ced

-0.14

ches

-0.14

POSITIVE LOGITS

ings

0.25

ed

0.24

ovan

0.22

able

0.20

edm

0.20

symbol

0.18

sworth

0.18

edImage

0.16

mates

0.16

ers

0.16

Activations Density 0.044%

terms related to folding and mold

No Comments

No Known Activations