INDEX

Explanations

various alphanumeric designations, possibly indicating model numbers or product 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

edback

-0.15

oose

-0.15

.Unmarshal

-0.14

TabIndex

-0.14

ToPoint

-0.14

AsyncResult

-0.14

imps

-0.14

uptools

-0.14

iband

-0.14

umbn

-0.13

POSITIVE LOGITS

=is

0.15

iy

0.14

weg

0.14

 upgrade

0.14

unma

0.13

âĸĪ

0.13

ÑĥÐ»Ð°

0.13

ily

0.13

cade

0.13

Cx

0.13

Activations Density 0.047%

various alphanumeric designations, possibly indicating model numbers or product identifiers

No Comments

No Known Activations