INDEX

Explanations

locations and affiliations of individuals or entities

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

istor

-0.18

å¯¹æĸ¹

-0.15

CONS

-0.14

stateParams

-0.14

oint

-0.14

Ð¾Ð»ÑĮÐ½Ð¾

-0.14

icator

-0.14

yme

-0.14

rzy

-0.14

criptors

-0.14

POSITIVE LOGITS

urm

0.16

thon

0.16

 physically

0.16

 Barton

0.14

 blank

0.14

orum

0.14

Urs

0.13

lash

0.13

inf

0.13

oux

0.13

Activations Density 0.051%

locations and affiliations of individuals or entities

No Comments

No Known Activations