INDEX

Explanations

terms related to computational elements and their characteristics within technological contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

èĩº

-0.16

elif

-0.16

ursal

-0.16

anke

-0.15

ÐºÑĥÐ»ÑĮ

-0.14

ãģ£ãģı

-0.14

Ã¤tt

-0.14

erce

-0.14

_glob

-0.14

tps

-0.13

POSITIVE LOGITS

bsub

0.15

lix

0.15

pton

0.15

.each

0.14

UDIO

0.14

emes

0.14

ESSAGES

0.13

 nech

0.13

avana

0.13

ÑĥÑĪ

0.13

Activations Density 0.298%

terms related to computational elements and their characteristics within technological contexts

No Comments

No Known Activations