INDEX

Explanations

concepts related to searching for ideas or information online

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

uber

-0.16

ummer

-0.16

_TestCase

-0.15

ukan

-0.15

 Greenwood

-0.15

erno

-0.15

ager

-0.14

Ð°Ð»Ñĥ

-0.14

lero

-0.14

ahoma

-0.14

POSITIVE LOGITS

 themselves

0.19

0.17

Ø¸

0.17

ystore

0.16

aar

0.16

Enumerable

0.16

omm

0.15

ung

0.15

elt

0.14

Sar

0.14

Activations Density 0.026%

concepts related to searching for ideas or information online

No Comments

No Known Activations