INDEX

Explanations

references to size or scale, specifically focusing on categories like "small" and "large"

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

-0.17

-0.15

ude

-0.14

é¤

-0.14

ede

-0.14

Nug

-0.14

ISA

-0.13

akt

-0.13

Alb

-0.13

POSITIVE LOGITS

 alike

0.23

 {{--<

0.14

quito

0.14

affles

0.14

ABCDEFGHIJKLMNOP

0.14

INGTON

0.14

ownt

0.14

opal

0.14

IRO

0.14

.CreateInstance

0.14

Activations Density 0.143%

references to size or scale, specifically focusing on categories like "small" and "large"

No Comments

No Known Activations