INDEX

Explanations

phrases indicating planning, decision-making, and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 microtime

-0.18

ElementsBy

-0.16

chner

-0.14

gesi

-0.14

iaux

-0.14

ÑĢÐµÑī

-0.14

dÃ¼l

-0.14

entrant

-0.14

klu

-0.14

 lÃłng

-0.14

POSITIVE LOGITS

ery

0.18

0.16

Ð¶Ð´

0.15

vala

0.15

wine

0.15

 defaultCenter

0.14

 synthetic

0.14

Top

0.14

fre

0.13

Activations Density 0.222%

phrases indicating planning, decision-making, and evaluations

No Comments

No Known Activations