INDEX

Explanations

proper nouns and technical terms related to various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

aju

-0.16

ahkan

-0.15

eka

-0.15

é¨

-0.14

ahun

-0.14

acs

-0.14

 Americ

-0.14

 turno

-0.14

izen

-0.14

KER

-0.14

POSITIVE LOGITS

 Vice

0.15

apia

0.14

 Wheeler

0.14

::-

0.14

builtin

0.14

 ìĪĺëıĦ

0.14

aned

0.14

aura

0.14

cc

0.14

Malloc

0.14

Activations Density 0.002%

proper nouns and technical terms related to various topics

No Comments

No Known Activations