INDEX

Explanations

keywords and phrases related to organizational or institutional identities and designs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ogenous

-0.16

yne

-0.15

orr

-0.15

Malloc

-0.15

ãĢģäºĮ

-0.14

ihan

-0.14

 Ø§ÙĦØªØŃ

-0.14

 btnCancel

-0.13

opak

-0.13

ulk

-0.13

POSITIVE LOGITS

chnitt

0.15

_atual

0.15

 icon

0.13

 slash

0.13

ìĸ¼

0.13

 ../../../

0.13

Ã±ana

0.13

 smelling

0.13

semicolon

0.13

Sum

0.13

Activations Density 0.078%

keywords and phrases related to organizational or institutional identities and designs

No Comments

No Known Activations