INDEX

Explanations

references to sample sizes and their details in research studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

lander

-0.21

aldo

-0.18

land

-0.17

-0.15

Baz

-0.15

ern

-0.15

iÄħ

-0.15

lands

-0.15

enne

-0.15

eenth

-0.15

POSITIVE LOGITS

/sample

0.25

.Sample

0.18

-lnd

0.17

aroo

0.17

ENCIL

0.17

TA

0.17

 mÃ£

0.16

MOOTH

0.16

-sample

0.16

plers

0.16

Activations Density 0.019%

references to sample sizes and their details in research studies

No Comments

No Known Activations