INDEX

Explanations

references to yoga and related activities

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

izyon

-0.17

 traces

-0.15

Ł³

-0.14

teb

-0.14

PUR

-0.14

.MixedReality

-0.13

verb

-0.13

ëģ¼

-0.13

 pupil

-0.13

POSITIVE LOGITS

istant

0.16

ruÅ¾

0.15

eyed

0.14

shiv

0.14

GLE

0.14

ÃĹ↵↵

0.13

osate

0.13

ëĦ·

0.13

mpl

0.13

ë¶Ħ

0.13

Activations Density 0.003%

references to yoga and related activities

No Comments

No Known Activations