INDEX

Explanations

phrases indicating statistical evaluation or comparisons

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

is

-0.17

 wherever

-0.14

if

-0.14

 Downing

-0.14

ro

-0.14

ro

-0.14

jobs

-0.14

rite

-0.13

at

-0.13

 strip

-0.13

POSITIVE LOGITS

enderit

0.16

BoxLayout

0.16

ëĵľë¦¬

0.16

aska

0.15

ÃŃÅ¾

0.14

LOB

0.14

ÅĻeb

0.14

avl

0.14

Ð¾ÑĩÐºÐ°

0.14

å¥Ķ

0.14

Activations Density 0.074%

phrases indicating statistical evaluation or comparisons

No Comments

No Known Activations