INDEX

Explanations

mentions of data security, classification, and privacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

arkin

-0.16

ucus

-0.15

 respir

-0.15

ilit

-0.14

iling

-0.14

erto

-0.14

 Party

-0.14

ien

-0.14

iler

-0.14

kl

-0.14

POSITIVE LOGITS

 fileprivate

0.18

Äįer

0.15

ãĥªãĤ«

0.14

raÃ§

0.14

Ø±ÙĬÙĥ

0.14

Ð±Ð¾Ð¼

0.14

OLVE

0.14

createElement

0.14

 Lowest

0.14

idla

0.14

Activations Density 0.034%

mentions of data security, classification, and privacy

No Comments

No Known Activations