INDEX

Explanations

descriptors related to fashion and style

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

odd

-0.15

-0.14

 cloth

-0.14

thon

-0.14

@@

-0.14

 surround

-0.14

 aide

-0.14

rieb

-0.14

kea

-0.13

entanyl

-0.13

POSITIVE LOGITS

 casual

0.21

midi

0.20

 statement

0.19

statement

0.18

 midi

0.18

Statement

0.17

 Statement

0.17

 Casual

0.17

 Midi

0.17

 causal

0.16

Activations Density 0.059%

descriptors related to fashion and style

No Comments

No Known Activations