INDEX

Explanations

the letter 'B' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ug

-0.19

rowser

-0.18

usch

-0.18

undle

-0.18

Ð¾ÑĢ

-0.18

Ð¾Ð³

-0.18

acker

-0.18

us

-0.18

io

-0.17

ucket

-0.17

POSITIVE LOGITS

em

0.20

oll

0.18

emd

0.17

antan

0.17

ellow

0.16

amber

0.16

rix

0.16

AN

0.16

ivariate

0.15

amel

0.15

Activations Density 0.139%

the letter 'B' in various contexts

No Comments

No Known Activations