INDEX

Explanations

proper nouns and specific identifiers related to people, places, or things

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

erule

-0.16

 burdens

-0.15

 Burke

-0.15

 Stanton

-0.15

isor

-0.14

van

-0.14

ibel

-0.14

ventory

-0.14

ÐµÑĢÐ¸Ð½

-0.14

 thá»ķ

-0.14

POSITIVE LOGITS

ohl

0.14

outers

0.14

 Pink

0.14

åħ»

0.14

athers

0.13

lico

0.13

.gov

0.13

Ã¡fico

0.13

_UNITS

0.13

aad

0.13

Activations Density 0.012%

proper nouns and specific identifiers related to people, places, or things

No Comments

No Known Activations