INDEX

Explanations

phrases that indicate a general consensus or commonality among people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

tabs

-0.15

abilitÃ©

-0.15

ensch

-0.14

atch

-0.14

á»©ng

-0.14

elib

-0.14

ypse

-0.14

Gab

-0.14

ialog

-0.14

ÑĥÑĢÐ½

-0.14

POSITIVE LOGITS

ãĥ³ãĥĦ

0.15

IRECTION

0.14

Ð¾ÑģÑĤÑĥÐ¿

0.14

deÅŁ

0.14

ichte

0.14

acci

0.14

SB

0.13

.camel

0.13

 chá»ĭ

0.13

Activations Density 0.081%

phrases that indicate a general consensus or commonality among people

No Comments

No Known Activations