INDEX

Explanations

phrases that indicate progression or achievement of goals

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

NSNotification

-0.18

AFX

-0.17

ClassLoader

-0.17

 Bilim

-0.15

Sharper

-0.15

fold

-0.14

ently

-0.14

hydrate

-0.14

SourceType

-0.13

ä¼¸

-0.13

POSITIVE LOGITS

idia

0.15

à¹Ĭ

0.15

ÑĨÐ¸Ð¾Ð½Ð°Ð»ÑĮ

0.14

 cmdline

0.14

plays

0.14

.assert

0.14

beer

0.14

lemetry

0.14

ãĥ¼ãĥ

0.14

pline

0.14

Activations Density 0.011%

phrases that indicate progression or achievement of goals

No Comments

No Known Activations