INDEX

Explanations

terms related to discovery and findings in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

_closure

-0.15

gradient

-0.15

isko

-0.15

iminal

-0.14

 carrier

-0.14

ÐµÐ»ÐµÐ¹

-0.13

upos

-0.13

acher

-0.13

ronic

-0.13

regon

-0.13

POSITIVE LOGITS

 Bart

0.15

hel

0.15

appen

0.14

ÑİÑĤ

0.14

ÅĪ

0.14

oko

0.14

RSS

0.13

 Babe

0.13

inin

0.13

fty

0.13

Activations Density 0.008%

terms related to discovery and findings in various contexts

No Comments

No Known Activations

terms related to discovery and findings in various contexts

No Comments

No Known Activations