INDEX

Explanations

numerical values and their contextual significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 fisse

-0.17

amp

-0.15

.lp

-0.14

isme

-0.13

inton

-0.13

Ã¼cken

-0.13

mint

-0.13

ostel

-0.13

adeon

-0.13

dera

-0.13

POSITIVE LOGITS

ugar

0.15

enario

0.14

 pathMatch

0.13

igator

0.13

wards

0.13

ingly

0.13

pollo

0.13

ABD

0.13

iversite

0.13

ç¼º

0.13

Activations Density 0.009%

numerical values and their contextual significance

No Comments

No Known Activations