INDEX

Explanations

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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ÄĽt

-0.17

oti

-0.17

alance

-0.16

Øª

-0.15

YA

-0.15

áºŃt

-0.15

eliac

-0.15

ajor

-0.15

-0.14

errat

-0.14

POSITIVE LOGITS

aked

0.20

asta

0.20

aket

0.18

omat

0.18

akes

0.18

ails

0.18

ailable

0.18

aken

0.18

ailing

0.18

etched

0.17

Activations Density 0.029%

the letter 'f' in various contexts

No Comments

No Known Activations