INDEX

Explanations

details about personal backgrounds and achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

neh

-0.16

din

-0.15

 sera

-0.15

.withOpacity

-0.14

leitung

-0.14

visor

-0.14

ceries

-0.14

itals

-0.14

Î³Î·

-0.14

isers

-0.13

POSITIVE LOGITS

gte

0.23

igte

0.18

NST

0.18

elt

0.18

zte

0.17

tte

0.17

kte

0.16

afort

0.16

onte

0.15

nte

0.15

Activations Density 0.032%

details about personal backgrounds and achievements

No Comments

No Known Activations