INDEX

Explanations

instances of the letter 'f' 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 @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ypy

-0.19

wert

-0.17

VERS

-0.16

ire

-0.15

vala

-0.15

itz

-0.15

oring

-0.15

throp

-0.15

PEG

-0.15

ires

-0.14

POSITIVE LOGITS

ic

0.19

ase

0.17

oment

0.16

iche

0.16

achu

0.16

het

0.15

ilde

0.15

ision

0.15

etic

0.15

idel

0.15

Activations Density 0.013%

instances of the letter 'f' in various contexts

No Comments

No Known Activations