INDEX

Explanations

references to characters and elements related to social interactions and community structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ÑĤÑĮ

-0.15

iyim

-0.14

bip

-0.14

erer

-0.14

 McConnell

-0.14

 Dixon

-0.14

apid

-0.14

ALAR

-0.13

oun

-0.13

ãģłãĤĪ

-0.13

POSITIVE LOGITS

 GÃ¶r

0.15

ÅĤu

0.15

uae

0.15

 attest

0.15

orgot

0.15

Ð»ÑıÐ½

0.14

Lux

0.14

jes

0.14

ìłĦìĹĲ

0.13

sep

0.13

Activations Density 0.075%

references to characters and elements related to social interactions and community structures

No Comments

No Known Activations