INDEX

Explanations

numerical values, particularly those pertaining to statistics or data measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

aka

-0.17

bes

-0.16

rad

-0.15

anda

-0.14

utsch

-0.14

 Siege

-0.14

 Society

-0.13

isbury

-0.13

ÏģÎ¹Î¬

-0.13

Dyn

-0.13

POSITIVE LOGITS

omy

0.18

ucz

0.16

Ã±ana

0.16

typings

0.15

áº±

0.14

iyon

0.14

ÑĥÑħ

0.14

OfClass

0.14

leet

0.13

ÅĻiv

0.13

Activations Density 0.032%

numerical values, particularly those pertaining to statistics or data measurements

No Comments

No Known Activations