INDEX

Explanations

words related to processes of democratization and visibility in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

urf

-0.16

ness

-0.15

ach

-0.15

NESS

-0.15

anye

-0.15

alc

-0.14

cot

-0.14

lessly

-0.14

umuz

-0.14

iver

-0.14

POSITIVE LOGITS

 fend

0.16

.scalablytyped

0.16

boz

0.15

azor

0.15

Ã¡ce

0.14

cce

0.14

ceae

0.14

/stretch

0.14

odega

0.14

ounters

0.14

Activations Density 0.251%

words related to processes of democratization and visibility in various contexts

No Comments

No Known Activations