INDEX

Explanations

abbreviations and initialisms related to technology and file formats

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

enko

-0.15

resse

-0.15

uzz

-0.15

brand

-0.15

inÃ¡

-0.14

Brand

-0.14

resenter

-0.14

jak

-0.14

_FOREACH

-0.14

POSITIVE LOGITS

ohan

0.19

oltip

0.17

rou

0.16

Ã¤nn

0.15

 sieve

0.14

orda

0.14

haus

0.13

alic

0.13

oin

0.13

atoon

0.13

Activations Density 0.002%

abbreviations and initialisms related to technology and file formats

No Comments

No Known Activations