INDEX

Explanations

actions related to planning and preparation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ALLE

-0.19

inte

-0.14

ald

-0.14

 Ð¾Ð±Ð»Ð°

-0.14

ela

-0.14

__,__

-0.14

aminer

-0.13

icho

-0.13

ÅŁtir

-0.13

 miss

-0.13

POSITIVE LOGITS

apper

0.16

osate

0.15

imens

0.15

.nii

0.14

 previously

0.14

 earlier

0.14

WR

0.14

 ages

0.14

ulan

0.14

 Harris

0.13

Activations Density 0.331%

actions related to planning and preparation

No Comments

No Known Activations