INDEX

Explanations

commands and instructions related to actions and behavior

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

COPE

-0.17

uÅ¡

-0.15

hum

-0.15

icks

-0.14

 myself

-0.14

illin

-0.14

anas

-0.14

eko

-0.14

hibit

-0.14

uyor

-0.14

POSITIVE LOGITS

aign

0.16

lÃ¡n

0.15

 Split

0.14

-append

0.14

 à¤®à¤¤

0.13

 à¤°à¤¹à¤¨

0.13

ÐµÐ½ÑĤÐ¸

0.13

 acceptance

0.13

-split

0.13

Activations Density 0.240%

commands and instructions related to actions and behavior

No Comments

No Known Activations