INDEX

Explanations

value propositions related to cost-effectiveness or worthwhile experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Gross

-0.17

EventListener

-0.16

gross

-0.16

isÃŃ

-0.15

Æ°ng

-0.15

 Pitch

-0.15

angelo

-0.15

ÌĨ

-0.14

antee

-0.14

 bergen

-0.14

POSITIVE LOGITS

ladesh

0.17

omentum

0.16

0.15

heel

0.15

nes

0.14

elper

0.14

our

0.14

paper

0.14

forth

0.14

aha

0.14

Activations Density 0.005%

value propositions related to cost-effectiveness or worthwhile experiences

No Comments

No Known Activations