INDEX

Explanations

numerical identifiers and codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Ones

-0.16

undle

-0.15

 miracle

-0.14

(enabled

-0.14

 impro

-0.14

lix

-0.14

oted

-0.13

ses

-0.13

 hack

-0.13

 disp

-0.13

POSITIVE LOGITS

rine

0.16

timeofday

0.16

CUS

0.16

KeyId

0.15

ÅĻeb

0.15

TOD

0.14

ãĥ³ãĥĸ

0.14

[section

0.13

éŀ

0.13

.requires

0.13

Activations Density 0.091%

numerical identifiers and codes

No Comments

No Known Activations