INDEX

Explanations

specific physical attributes or notable characteristics

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

strap

-0.15

ç¢°

-0.14

sons

-0.14

ihan

-0.14

arend

-0.14

acent

-0.14

ì´

-0.14

inou

-0.13

 carriers

-0.13

ahir

-0.13

POSITIVE LOGITS

 speaks

0.17

 speak

0.17

spe

0.16

.say

0.16

 tells

0.15

 speaking

0.15

_nat

0.15

Ð¾Ð·

0.15

/location

0.15

ikel

0.15

Activations Density 0.006%

specific physical attributes or notable characteristics

No Comments

No Known Activations