INDEX

Explanations

references to historical contexts and changes in societal norms

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

çĽ®åīį

-0.17

ucus

-0.15

 ìĿ´ë²Ī

-0.14

heid

-0.14

uf

-0.14

Mahon

-0.14

 lately

-0.13

 ÂłÂł ÂłÂł

-0.13

chw

-0.13

Ã¥r

-0.13

POSITIVE LOGITS

era

0.23

 back

0.22

(before

0.21

 weren

0.20

Era

0.19

.Today

0.19

-era

0.17

Primitive

0.17

back

0.16

 wasn

0.16

Activations Density 0.187%

references to historical contexts and changes in societal norms

No Comments

No Known Activations