INDEX

Explanations

references to influences or sources within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ignum

-0.18

nete

-0.16

.sourceforge

-0.16

ivec

-0.15

iliz

-0.15

Ã¡bado

-0.15

.UnitTesting

-0.15

_KP

-0.15

abet

-0.14

ARRANT

-0.14

POSITIVE LOGITS

ats

0.16

0.15

Pul

0.14

ÑĤÐ¾Ð³Ð¾

0.14

UGIN

0.14

QRS

0.13

 solic

0.13

osa

0.13

Enc

0.13

Activations Density 0.098%

references to influences or sources within a context

No Comments

No Known Activations