INDEX

Explanations

references to locations, particularly addresses or numerical identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

icker

-0.18

-0.17

-0.16

CCCCCC

-0.15

ctl

-0.15

ilight

-0.15

fat

-0.15

 Scre

-0.15

on

-0.15

POSITIVE LOGITS

AUSE

0.16

wcs

0.16

AME

0.16

ÑıÐ²Ð¸

0.16

emy

0.15

ause

0.15

Resize

0.15

podob

0.14

ALCHEMY

0.14

-haspopup

0.14

Activations Density 0.053%

references to locations, particularly addresses or numerical identifiers

No Comments

No Known Activations