INDEX

Explanations

terms related to binocular vision and visual phenomena

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

encing

-0.16

rene

-0.15

strup

-0.15

ÙħÙĨØª

-0.15

ampie

-0.15

aliz

-0.14

aba

-0.14

rej

-0.14

ide

-0.14

irit

-0.14

POSITIVE LOGITS

Ð±Ð¾Ð»

0.14

Const

0.14

 Harden

0.14

 tráº¥n

0.13

vision

0.13

ARED

0.13

asar

0.13

ffer

0.13

_ISO

0.13

frag

0.13

Activations Density 0.198%

terms related to binocular vision and visual phenomena

No Comments

No Known Activations