INDEX

Explanations

words and phrases related to job roles and responsibilities

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

Ð°Ð½Ð¸ÑĨ

-0.18

idis

-0.16

utschen

-0.15

_usec

-0.15

kil

-0.15

Ð´Ð°Ð¿

-0.15

ilip

-0.14

krit

-0.14

autoload

-0.14

 Ø§ÙĦØªØ±

-0.14

POSITIVE LOGITS

iate

0.16

.shtml

0.15

0.14

iot

0.14

ism

0.14

Ned

0.14

ddl

0.14

ens

0.14

Ni

0.14

Activations Density 0.037%

words and phrases related to job roles and responsibilities

No Comments

No Known Activations