INDEX

Explanations

phrases related to measurements and statistical estimates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ario

-0.17

side

-0.17

 tslib

-0.15

FP

-0.15

udson

-0.15

 side

-0.14

 sidew

-0.14

 Bour

-0.14

uncan

-0.14

å½

-0.14

POSITIVE LOGITS

Intermediate

0.17

 Intermediate

0.17

 -*-č↵

0.16

ipers

0.15

ãĥ³ãĥķ

0.15

 past

0.15

 Paste

0.15

ceptive

0.14

.Factory

0.14

iÃª

0.14

Activations Density 0.191%

phrases related to measurements and statistical estimates

No Comments

No Known Activations