INDEX

Explanations

occurrences of references to people and their respective identifiers

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

åıį

-0.18

WER

-0.16

hardt

-0.16

NewProp

-0.15

ubby

-0.14

heed

-0.14

Xxx

-0.14

ioc

-0.14

.twig

-0.14

ullet

-0.14

POSITIVE LOGITS

 warm

0.15

Mes

0.14

beg

0.14

Beg

0.14

div

0.13

fle

0.13

 directive

0.13

 insp

0.13

ble

0.13

ich

0.13

Activations Density 0.002%

occurrences of references to people and their respective identifiers

No Comments

No Known Activations