INDEX

Explanations

phrases indicating perception or opinion about individuals or topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

.uf

-0.17

á»ĩ

-0.15

.FontStyle

-0.15

ersist

-0.14

 Alone

-0.14

illis

-0.14

nest

-0.14

 Marketable

-0.14

mania

-0.14

Ãªt

-0.14

POSITIVE LOGITS

oad

0.16

vit

0.15

hurst

0.15

hof

0.14

 favourite

0.14

ios

0.14

Ted

0.14

 sund

0.14

ivo

0.13

-len

0.13

Activations Density 0.193%

phrases indicating perception or opinion about individuals or topics

No Comments

No Known Activations