INDEX

Explanations

phrases indicating conditionality or variability based on circumstances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ses

-0.16

amburger

-0.16

 defa

-0.15

Ø§Ø¦Ø¨

-0.15

adel

-0.14

uled

-0.14

ATTRIBUTE

-0.14

opis

-0.14

lijke

-0.14

sko

-0.14

POSITIVE LOGITS

 depending

0.16

æ¬ł

0.15

 time

0.15

iate

0.14

åīĳ

0.14

 Ð¿ÑĢÐ¸ÑħÐ¾Ð´

0.14

ior

0.14

ether

0.13

ndef

0.13

Activations Density 0.019%

phrases indicating conditionality or variability based on circumstances

No Comments

No Known Activations