INDEX

Explanations

conjunctions and words related to processes and evaluations

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

untas

-0.15

ãģ£ãģ¨

-0.15

angl

-0.15

Margins

-0.14

olars

-0.14

ulas

-0.13

ionario

-0.13

leurs

-0.13

atra

-0.13

Ø¯Ø§Ø±

-0.13

POSITIVE LOGITS

ednou

0.15

quential

0.14

rze

0.14

ÏĢÎŃ

0.14

 KrÃ¡l

0.14

NetMessage

0.14

rites

0.14

£½

0.14

ãĤħ

0.13

æī£

0.13

Activations Density 0.002%

conjunctions and words related to processes and evaluations

No Comments

No Known Activations