INDEX

Explanations

references to geographical locations and their descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

anken

-0.18

Clr

-0.16

ibraries

-0.15

ActionCreators

-0.15

/***/

-0.15

Ð»Ð¸ÑĪ

-0.14

ulture

-0.14

.school

-0.14

ãĥ¼ãĥł

-0.14

ncia

-0.14

POSITIVE LOGITS

 central

0.25

 rural

0.20

 suburban

0.19

 northern

0.19

 Northwestern

0.18

nor

0.17

 downtown

0.17

-central

0.17

central

0.17

mid

0.17

Activations Density 0.214%

references to geographical locations and their descriptions

No Comments

No Known Activations