INDEX

Explanations

sequences of numerical or mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

uala

-0.15

vecs

-0.14

abei

-0.14

iram

-0.13

igy

-0.13

LESS

-0.13

appa

-0.13

 Manson

-0.13

apa

-0.13

POSITIVE LOGITS

 Ð¿Ð¾Ð¶

0.18

blick

0.15

onne

0.15

0.14

lear

0.14

UNK

0.13

erm

0.13

etail

0.13

 interventions

0.13

Activations Density 0.084%

sequences of numerical or mathematical expressions

No Comments

No Known Activations