INDEX

Explanations

instances of naming or listing items or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

rey

-0.15

esel

-0.15

ynes

-0.15

rome

-0.14

anio

-0.14

icket

-0.14

:animated

-0.14

inds

-0.14

arta

-0.13

POSITIVE LOGITS

eldorf

0.14

aura

0.14

earable

0.14

uhn

0.14

 forg

0.14

ithub

0.13

.cz

0.13

oose

0.13

aycast

0.13

apol

0.13

Activations Density 0.008%

instances of naming or listing items or concepts

No Comments

No Known Activations