INDEX

Explanations

instances of certain charactes or phrases related to being in a specific place or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 nackte

-0.18

essel

-0.16

Ð°Ð½ÑĤÐ°Ð¶

-0.16

atar

-0.15

chaft

-0.15

rad

-0.15

Î¸ÎµÎ½

-0.14

aska

-0.14

feit

-0.14

Rad

-0.14

POSITIVE LOGITS

ÐµÐ½Ð½Ð¾

0.19

Ð¾ÑĢÑĥÐ¶

0.19

 Ð²ÑĢÐµÐ¼Ñı

0.18

 Ð²ÑĤÐ¾ÑĢ

0.17

ÐµÐ´Ð¸

0.17

 ÐĽÑĮÐ²

0.17

 Ð¸Ð¼Ñı

0.17

 Ð²Ð»Ð°

0.16

 Ð´Ð²Ð¾ÑĢ

0.16

 Ð¼Ð½Ð¾Ð³Ð¸Ñħ

0.16

Activations Density 0.003%

instances of certain charactes or phrases related to being in a specific place or context

No Comments

No Known Activations