INDEX

Explanations

words and phrases related to painful or distressing experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ODE

-0.17

èĪ¬

-0.16

erate

-0.15

ibilities

-0.14

 ìĭ

-0.14

anlar

-0.14

Äĥm

-0.14

Ø¨Ø´

-0.14

(s

-0.14

ìĬ¤íģ¬

-0.14

POSITIVE LOGITS

ness

0.22

NESS

0.16

dorf

0.16

á»¥y

0.16

ieri

0.15

 adjective

0.15

ROTO

0.15

CHANT

0.15

atable

0.15

nict

0.14

Activations Density 0.231%

words and phrases related to painful or distressing experiences

No Comments

No Known Activations