INDEX

Explanations

expressions of preference or affinity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ranÃŃ

-0.14

iel

-0.14

sheet

-0.14

.IMAGE

-0.14

sb

-0.13

ainment

-0.13

 BOOT

-0.13

allon

-0.13

opia

-0.13

reira

-0.13

POSITIVE LOGITS

bounding

0.15

edu

0.14

InRange

0.14

 Watson

0.14

ht

0.14

 Hutchinson

0.14

ki

0.14

kan

0.14

Warning

0.14

 SetProperty

0.13

Activations Density 0.012%

expressions of preference or affinity

No Comments

No Known Activations