INDEX

Explanations

possessive forms and references to notable locations or buildings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

readcr

-0.18

vem

-0.16

INA

-0.15

ãĤ¿ãĥ«

-0.15

_LD

-0.15

alli

-0.15

Ð»Ð¸Ð²

-0.14

ëŁ

-0.14

arat

-0.14

sak

-0.14

POSITIVE LOGITS

esz

0.15

lee

0.14

lok

0.14

 Buen

0.14

ough

0.14

bul

0.14

hub

0.13

Bon

0.13

loo

0.13

Activations Density 0.008%

possessive forms and references to notable locations or buildings

No Comments

No Known Activations