INDEX

Explanations

concepts related to improvement and enhancement

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

lor

-0.15

aron

-0.15

plet

-0.14

minus

-0.14

ADR

-0.13

 Yourself

-0.13

UES

-0.13

UGE

-0.13

ysis

-0.13

POSITIVE LOGITS

 itself

0.17

/help

0.17

emmel

0.16

czy

0.16

fdc

0.16

our

0.15

etsk

0.15

 your

0.15

-enable

0.15

Ã³nico

0.15

Activations Density 0.221%

concepts related to improvement and enhancement

No Comments

No Known Activations