INDEX

Explanations

references to measurements and data-related metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

AdapterFactory

-0.16

ultipart

-0.15

_tac

-0.15

 gear

-0.14

rine

-0.14

ighton

-0.14

à¥įà¤Ľ

-0.14

 talep

-0.14

Gear

-0.14

LAR

-0.13

POSITIVE LOGITS

ãĥĥãĥĪ

0.15

gu

0.15

 Tort

0.14

UTTON

0.14

elli

0.14

cl

0.14

ember

0.14

cle

0.14

red

0.13

Refreshing

0.13

Activations Density 0.013%

references to measurements and data-related metrics

No Comments

No Known Activations