INDEX

Explanations

terms related to hollowness or hollow structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

agle

-0.17

ÏģÎ¯

-0.15

auge

-0.15

Ãłnh

-0.15

timeofday

-0.14

Åĳs

-0.14

RLF

-0.14

liche

-0.14

 expulsion

-0.14

exp

-0.14

POSITIVE LOGITS

istrovstvÃŃ

0.17

 Helm

0.16

parison

0.16

space

0.15

 hollow

0.14

ca

0.14

ities

0.14

aho

0.14

ÑĩÐ°ÑĤ

0.14

Activations Density 0.044%

terms related to hollowness or hollow structures

No Comments

No Known Activations