INDEX

Explanations

information related to names and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ichick

-0.16

'icon

-0.14

 labeling

-0.14

KF

-0.14

zan

-0.14

 Prometheus

-0.13

itoris

-0.13

à¤¾à¤ģ

-0.13

ogg

-0.13

uw

-0.13

POSITIVE LOGITS

 last

0.42

 Last

0.38

 given

0.38

-last

0.36

Last

0.35

given

0.35

last

0.34

 Given

0.34

_last

0.34

 LAST

0.34

Activations Density 0.149%

information related to names and their attributes

No Comments

No Known Activations