INDEX

Explanations

references to time duration and frequency

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

rrha

-0.18

áº©u

-0.16

_rwlock

-0.16

ioni

-0.15

ãĤįãģĨ

-0.15

uner

-0.15

eless

-0.15

amburger

-0.15

endereco

-0.15

-0.14

POSITIVE LOGITS

 decades

0.20

jak

0.20

beros

0.17

pul

0.17

 centuries

0.17

uhl

0.16

ystal

0.16

 century

0.16

Kad

0.15

ÛĮÙĨÙĩ

0.15

Activations Density 0.060%

references to time duration and frequency

No Comments

No Known Activations