INDEX

Explanations

phrases related to remnants and traces of past structures or civilizations

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

ãĥ³ãĤ°

-0.15

 Ø§ÙĦØµÙģ

-0.14

gow

-0.14

META

-0.14

CharArray

-0.14

wend

-0.14

.cn

-0.14

ennie

-0.13

embro

-0.13

ÑģÑĤÐ°Ð½

-0.13

POSITIVE LOGITS

ents

0.16

ruise

0.15

Ã§as

0.14

elden

0.14

iform

0.14

 pieces

0.14

pieces

0.14

 Clearance

0.14

acent

0.14

/new

0.14

Activations Density 0.046%

phrases related to remnants and traces of past structures or civilizations

No Comments

No Known Activations