INDEX

Explanations

instances of quantitative measurements or comparative language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ã©ra

-0.16

ãĥ¬ãĥĵ

-0.16

 IReadOnly

-0.15

TestingModule

-0.15

licted

-0.14

ÏĦÎ¹ÎºÎ¿

-0.14

ulsion

-0.14

icator

-0.14

ÐºÑĢÐ°

-0.14

ccione

-0.14

POSITIVE LOGITS

 human

0.20

 Human

0.19

human

0.17

_human

0.17

Human

0.16

acher

0.16

UMAN

0.16

 eventually

0.15

 humans

0.15

-human

0.15

Activations Density 0.009%

instances of quantitative measurements or comparative language

No Comments

No Known Activations