INDEX

Explanations

terms related to presenters in various contexts

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

los

-0.16

mani

-0.16

_PTR

-0.15

 Entr

-0.15

inson

-0.14

endez

-0.14

apy

-0.13

least

-0.13

 Spotlight

-0.13

POSITIVE LOGITS

herits

0.17

Ð´Ð¸Ð½Ð°

0.15

tings

0.15

IFDEF

0.15

nid

0.15

elter

0.14

exclusive

0.14

äº¡

0.14

edImage

0.14

ÑĢÐ¾Ð³

0.14

Activations Density 0.064%

terms related to presenters in various contexts

No Comments

No Known Activations