INDEX

Explanations

phrases indicating requirements and procedural steps

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

usz

-0.19

etus

-0.16

.Metro

-0.15

ettes

-0.15

Dek

-0.15

frauen

-0.15

Ãªs

-0.15

bach

-0.14

etz

-0.14

tram

-0.14

POSITIVE LOGITS

RLF

0.16

 Lilly

0.15

oom

0.14

ocha

0.14

.pad

0.14

.logic

0.13

Rum

0.13

pad

0.13

Lov

0.13

é¥

0.13

Activations Density 0.358%

phrases indicating requirements and procedural steps

No Comments

No Known Activations