INDEX

Explanations

proper nouns, particularly names of organizations and places

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

odate

-0.16

 McCabe

-0.15

Î¹Ïĩ

-0.15

è¢ĭ

-0.15

AMED

-0.14

cio

-0.14

$LANG

-0.14

ISIBLE

-0.14

áº«n

-0.14

alous

-0.13

POSITIVE LOGITS

à¸¯

0.24

ETO

0.15

lat

0.15

ensis

0.15

oro

0.15

macen

0.14

 Pradesh

0.14

 Patel

0.14

ulk

0.14

Activations Density 0.079%

proper nouns, particularly names of organizations and places

No Comments

No Known Activations