INDEX

Explanations

unique characters and symbols, particularly in a context of scientific or technical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

_clear

-0.17

Clear

-0.17

 Clearance

-0.17

 Clear

-0.16

_Clear

-0.16

 CLEAR

-0.16

CLEAR

-0.16

 clearance

-0.15

.Master

-0.15

 Clears

-0.14

POSITIVE LOGITS

 Graves

0.16

ategory

0.16

 Face

0.16

Fac

0.15

 shrink

0.15

Hyp

0.15

eson

0.14

 what

0.14

éĻµ

0.14

Fac

0.14

Activations Density 0.005%

unique characters and symbols, particularly in a context of scientific or technical information

No Comments

No Known Activations