INDEX

Explanations

mentions of the name "Lisa."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

leigh

-0.16

ãĤīãģĹ

-0.15

utan

-0.15

rott

-0.14

kan

-0.14

Ð½Ð°ÑĢ

-0.14

µ

-0.13

 mekt

-0.13

essa

-0.13

ä½ĵ

-0.13

POSITIVE LOGITS

reme

0.18

-Mar

0.16

andro

0.15

mania

0.15

.ov

0.14

.tt

0.14

 Marie

0.14

fulness

0.14

amma

0.14

edList

0.14

Activations Density 0.008%

mentions of the name "Lisa."

No Comments

No Known Activations