INDEX

Explanations

references to canned food and preservation methods

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

emoc

-0.16

agn

-0.15

 themed

-0.14

wig

-0.14

å¥Ī

-0.14

indr

-0.14

Ul

-0.14

 reck

-0.13

rary

-0.13

artin

-0.13

POSITIVE LOGITS

UNU

0.15

itan

0.14

lung

0.14

akan

0.14

ermen

0.14

uet

0.14

ensa

0.13

NSK

0.13

kers

0.13

ibile

0.13

Activations Density 0.027%

references to canned food and preservation methods

No Comments

No Known Activations