INDEX

Explanations

references to locations or places of significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

itler

-0.17

odies

-0.16

jez

-0.15

orsi

-0.14

ofile

-0.14

UDA

-0.14

à¸´à¹ī

-0.14

ãĥĴ

-0.14

strand

-0.14

getAs

-0.14

POSITIVE LOGITS

IR

0.18

Ir

0.17

ForObject

0.17

ir

0.16

IR

0.16

ben

0.16

ven

0.15

Pf

0.15

Ir

0.15

Activations Density 0.032%

references to locations or places of significance

No Comments

No Known Activations