INDEX

Explanations

specific numerical data or identifiers related to addresses and contact information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

camp

-0.18

ens

-0.16

chan

-0.16

hei

-0.16

enc

-0.16

ob

-0.15

ple

-0.15

ossip

-0.15

ters

-0.15

vara

-0.15

POSITIVE LOGITS

ussen

0.17

igo

0.16

quette

0.16

ably

0.15

rophe

0.15

baugh

0.15

woord

0.15

Ð°Ð³Ð°ÑĤÐ¾

0.14

rak

0.14

agnar

0.14

Activations Density 0.135%

specific numerical data or identifiers related to addresses and contact information

No Comments

No Known Activations