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 @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ots

-0.20

aptop

-0.18

ikes

-0.18

ike

-0.18

ABS

-0.17

ance

-0.17

ink

-0.16

abs

-0.16

ift

-0.16

ocking

-0.16

POSITIVE LOGITS

lund

0.20

usat

0.18

om

0.17

elow

0.17

el

0.17

estring

0.16

ekim

0.16

 Shields

0.16

utos

0.15

ill

0.15

Activations Density 0.031%

occurrences of the letter 'L' in various contexts

No Comments

No Known Activations