INDEX

Explanations

references to blog content and articles, particularly those relating to analysis and insights

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

edik

-0.15

estruct

-0.14

agues

-0.14

:::::

-0.14

Destroyed

-0.13

uren

-0.13

aldi

-0.13

Ã¡Äį

-0.13

ÐŁÐļ

-0.13

POSITIVE LOGITS

 Spoon

0.16

isl

0.15

ativ

0.15

 crunch

0.14

ÑĤÐ°Ð»

0.14

artz

0.14

 neutrality

0.14

CF

0.14

 Lans

0.14

ova

0.13

Activations Density 0.253%

references to blog content and articles, particularly those relating to analysis and insights

No Comments

No Known Activations