INDEX

Explanations

references to parallel processing and distributed computing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

tfoot

-0.18

iros

-0.16

ford

-0.16

-urlencoded

-0.15

emoc

-0.15

disposing

-0.15

chten

-0.14

raw

-0.14

morgan

-0.14

rava

-0.14

POSITIVE LOGITS

mit

0.16

edImage

0.16

avo

0.15

Ã¶z

0.14

bor

0.14

averse

0.14

ida

0.14

_QMARK

0.13

Activations Density 0.052%

references to parallel processing and distributed computing

No Comments

No Known Activations