INDEX

Explanations

words related to "amps" and "ramp," often in contexts involving measurement, intensity, or music

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

er

-0.20

Ø±

-0.19

rnd

-0.19

lsen

-0.16

RF

-0.16

rand

-0.15

lim

-0.15

lib

-0.15

erals

-0.15

POSITIVE LOGITS

agne

0.20

ieri

0.20

ylon

0.20

site

0.18

stead

0.18

shire

0.18

aign

0.17

adoo

0.17

assador

0.17

0.16

Activations Density 0.031%

words related to "amps" and "ramp," often in contexts involving measurement, intensity, or music

No Comments

No Known Activations