INDEX

Explanations

technical references to memory and RAM specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ox

-0.15

ahoma

-0.15

\Mapping

-0.15

genes

-0.14

ifle

-0.14

 detain

-0.13

iyim

-0.13

.mi

-0.13

binary

-0.13

POSITIVE LOGITS

ç©į

0.16

Cul

0.15

ç©

0.15

Ã¸r

0.15

deb

0.15

pent

0.15

ati

0.14

agner

0.14

lyn

0.14

yl

0.14

Activations Density 0.004%

technical references to memory and RAM specifications

No Comments

No Known Activations