INDEX

Explanations

phrases or symbols indicating presence or existence in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

_TestCase

-0.15

INF

-0.14

 ===>

-0.14

ë³¸

-0.14

otlin

-0.14

èħ

-0.14

ihn

-0.14

 GOODMAN

-0.14

uien

-0.14

ë¨

-0.14

POSITIVE LOGITS

0.16

 contributions

0.16

 network

0.16

 mechanism

0.16

 Thousand

0.15

 encounter

0.15

 neutral

0.15

Me

0.15

 contribution

0.14

 interests

0.14

Activations Density 0.002%

phrases or symbols indicating presence or existence in various contexts

No Comments

No Known Activations