INDEX

Explanations

phrases related to evaluating or analyzing situations and their consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ogn

-0.17

ktor

-0.16

Ĺ

-0.15

elho

-0.14

annes

-0.14

olta

-0.14

 Century

-0.14

ampler

-0.14

oce

-0.13

oenix

-0.13

POSITIVE LOGITS

êµĲ

0.15

aster

0.15

.LENGTH

0.15

 Magnus

0.14

_iff

0.14

\Carbon

0.14

xis

0.14

okit

0.14

ule

0.13

Activations Density 0.129%

phrases related to evaluating or analyzing situations and their consequences

No Comments

No Known Activations