INDEX

Explanations

unique identifiers or specialized symbols, particularly in a technical or academic context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ixin

-0.15

Implemented

-0.14

ifu

-0.14

paths

-0.13

 rencont

-0.13

aksi

-0.13

arel

-0.13

PCP

-0.13

wald

-0.13

akan

-0.13

POSITIVE LOGITS

UN

0.24

UN

0.19

 programme

0.18

 incumbent

0.17

.UN

0.16

UNS

0.16

 duty

0.16

 substantive

0.16

UNIT

0.16

 corporate

0.15

Activations Density 0.005%

unique identifiers or specialized symbols, particularly in a technical or academic context

No Comments

No Known Activations