INDEX

Explanations

terms related to rankings and positions in competitions or evaluations

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

elden

-0.16

ova

-0.15

ibble

-0.15

gio

-0.15

angler

-0.15

ocks

-0.14

 initially

-0.14

Ø±ÙĪØ³

-0.14

ilm

-0.14

wu

-0.14

POSITIVE LOGITS

hots

0.18

ellar

0.17

erten

0.16

ars

0.16

rador

0.15

ARS

0.15

Ã¼m

0.14

esel

0.14

ê´ĳ

0.14

ãĤ»ãĥ³

0.14

Activations Density 0.003%

terms related to rankings and positions in competitions or evaluations

No Comments

No Known Activations