INDEX

Explanations

phrases and terms that suggest inclusion or belonging

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Hess

-0.16

spm

-0.15

VILLE

-0.14

ulus

-0.14

á»¯

-0.14

 deal

-0.14

htable

-0.14

ÙĪØ§Ø²

-0.14

å¥ı

-0.14

ìĿ´ìĸ´

-0.13

POSITIVE LOGITS

osto

0.21

osta

0.17

amac

0.15

aming

0.15

orsk

0.14

-mf

0.14

Ã³a

0.14

edn

0.14

 Painter

0.14

cola

0.14

Activations Density 0.003%

phrases and terms that suggest inclusion or belonging

No Comments

No Known Activations