INDEX

Explanations

instances of the word "log" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ystone

-0.17

ADS

-0.15

 addCriterion

-0.15

 downs

-0.15

udent

-0.15

èģŀ

-0.15

ufs

-0.15

neh

-0.15

alte

-0.15

Forward

-0.14

POSITIVE LOGITS

onation

0.20

on

0.19

 onto

0.19

-on

0.19

ON

0.18

off

0.17

 yourself

0.17

 trá»±c

0.17

ãĤªãĥ³

0.17

oeff

0.16

Activations Density 0.011%

instances of the word "log" and its variations

No Comments

No Known Activations

instances of the word "log" and its variations

No Comments

No Known Activations