INDEX

Explanations

terms related to data input and output in programming or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

_inputs

-0.16

usto

-0.16

ophon

-0.15

Inputs

-0.15

yor

-0.15

egg

-0.15

abeth

-0.15

/is

-0.15

ê¸ī

-0.15

å¿ľ

-0.14

POSITIVE LOGITS

ting

0.63

ted

0.60

ters

0.47

/output

0.44

TING

0.41

ter

0.36

tings

0.35

-output

0.35

ty

0.28

ten

0.27

Activations Density 0.039%

terms related to data input and output in programming or technical contexts

No Comments

No Known Activations