INDEX

Explanations

phrases related to characteristics or conditions that involve "being" or "existence."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ereo

-0.16

RIES

-0.15

imson

-0.15

ienen

-0.14

zcze

-0.14

à¤¿à¤¯à¤¤

-0.14

retorno

-0.14

 PhÃ¡t

-0.14

 æŁ

-0.14

 prolong

-0.14

POSITIVE LOGITS

loor

0.15

Î¸Î·

0.14

 tabindex

0.13

vac

0.13

ÑĩÐµÑĢ

0.13

 typical

0.13

ascar

0.13

irket

0.13

#/

0.13

Activations Density 0.206%

phrases related to characteristics or conditions that involve "being" or "existence."

No Comments

No Known Activations