INDEX

Explanations

references to broad or expansive contexts within various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ennai

-0.17

zl

-0.16

enn

-0.15

 Blond

-0.15

iec

-0.15

istrovstvÃŃ

-0.14

 Ð¾Ð±Ð»Ð¸Ñĩ

-0.14

.hxx

-0.14

Ð¾Ð²Ð°Ð½Ð°

-0.14

agner

-0.14

POSITIVE LOGITS

anging

0.16

_elt

0.15

ahren

0.14

 wider

0.14

 community

0.14

mÃŃn

0.14

endar

0.13

 QuÃ©

0.13

Activations Density 0.019%

references to broad or expansive contexts within various subjects

No Comments

No Known Activations