INDEX

Explanations

names of authors and literary works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Ð¶ÐµÐ½

-0.15

 ÐºÐ°Ñģ

-0.15

_mgr

-0.14

åµ

-0.14

 broken

-0.14

seau

-0.14

itate

-0.14

riers

-0.14

POSITIVE LOGITS

bour

0.15

 Wich

0.14

pone

0.14

æİĴ

0.14

ÎŃÎ»

0.14

ÂłPS

0.14

Ø§Ø®

0.14

pgsql

0.14

NL

0.13

bah

0.13

Activations Density 0.016%

names of authors and literary works

No Comments

No Known Activations