INDEX

Explanations

terms related to writing and documentation processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 bottleneck

-0.15

Ø§Ø¨ÙĬ

-0.14

.isArray

-0.14

usz

-0.14

mb

-0.14

ysz

-0.14

-tm

-0.14

fold

-0.14

idel

-0.14

ergus

-0.13

POSITIVE LOGITS

ÃĲ

0.17

_tD

0.15

 Royale

0.15

lingen

0.15

itzer

0.15

_tC

0.14

alone

0.14

 happier

0.14

rips

0.14

opers

0.14

Activations Density 0.044%

terms related to writing and documentation processes

No Comments

No Known Activations