INDEX

Explanations

geographical directions and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.17

ÑĢÑĥÐ½

-0.17

emouth

-0.15

Ø§Ø¡Ø©

-0.15

chy

-0.15

 velit

-0.14

Ù¾Ø³

-0.14

æģµ

-0.14

 stag

-0.14

iphy

-0.14

POSITIVE LOGITS

zer

0.16

Cad

0.14

HITE

0.14

Cad

0.13

guard

0.13

abs

0.13

 Raqqa

0.13

 Ã©l

0.13

itas

0.13

 charge

0.13

Activations Density 0.006%

geographical directions and locations

No Comments

No Known Activations