INDEX

Explanations

code snippets and technical specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anki

-0.16

()(

-0.14

nze

-0.14

zano

-0.13

aliyet

-0.13

scribe

-0.13

 Spiral

-0.13

 éĺ

-0.13

ilt

-0.13

 Dawson

-0.13

POSITIVE LOGITS

zem

0.18

creature

0.17

 creature

0.17

 ë´Ĳ

0.15

.infinity

0.15

uta

0.15

 vess

0.14

 YÃ¶n

0.14

eof

0.14

vÃ¡l

0.14

Activations Density 0.193%

code snippets and technical specifications

No Comments

No Known Activations