INDEX

Explanations

references to repeated experiences or patterns of behavior over time

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

bih

-0.15

bas

-0.14

-0.13

ãĥ¼ãĥĹ

-0.13

uns

-0.13

Ð»ÑĸÐ´

-0.13

kanÄ±

-0.13

Ø¶Ø©

-0.13

XXXXXXXX

-0.13

ÃŃm

-0.13

POSITIVE LOGITS

 particular

0.16

 unlike

0.16

 láº§n

0.15

Ã¶y

0.15

áº¤

0.15

rawer

0.14

 åĿ

0.14

iggins

0.14

aban

0.14

 latest

0.14

Activations Density 0.212%

references to repeated experiences or patterns of behavior over time

No Comments

No Known Activations