INDEX

Explanations

descriptors and attributes related to aesthetics and details in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ÄĽÅ¾

-0.15

iddet

-0.15

@js

-0.15

/repos

-0.14

_INCLUDED

-0.14

 ç±

-0.14

ÙĥØ²

-0.14

ANDOM

-0.13

(comb

-0.13

 Ø§ÙĦÙħØªØŃØ¯Ø©

-0.13

POSITIVE LOGITS

acc

0.22

 accessor

0.19

 fest

0.19

fle

0.19

re

0.18

 deck

0.17

aw

0.17

0.16

 pattern

0.16

 heavy

0.16

Activations Density 0.248%

descriptors and attributes related to aesthetics and details in various contexts

No Comments

No Known Activations