INDEX

Explanations

references to locations or points of interest

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ude

-0.15

zip

-0.15

istan

-0.15

èĩ£

-0.15

_AR

-0.14

erie

-0.14

LEAR

-0.14

pane

-0.14

æķħ

-0.14

ensi

-0.13

POSITIVE LOGITS

alous

0.16

 Ãĩev

0.15

icamente

0.15

appers

0.14

ovic

0.14

åĽ

0.14

ovice

0.14

lessly

0.14

 Ø³ÙĦ

0.14

åĩ¡

0.13

Activations Density 0.012%

references to locations or points of interest

No Comments

No Known Activations