INDEX

Explanations

occurrences of the letter 'l' 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 @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

.mods

-0.17

ytt

-0.16

chy

-0.16

gens

-0.16

thora

-0.15

eniz

-0.15

 Coul

-0.14

ynes

-0.14

.gdx

-0.14

ILES

-0.14

POSITIVE LOGITS

ata

0.35

ÄĻ

0.22

Äħd

0.21

Äħ

0.21

utow

0.21

Å¼e

0.21

ud

0.20

icz

0.20

ekt

0.19

ecz

0.19

Activations Density 0.006%

occurrences of the letter 'l' in various contexts

No Comments

No Known Activations