INDEX

Explanations

specific numbers or numeric sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

åĳ

-0.15

iben

-0.15

bed

-0.14

atrix

-0.14

Ih

-0.14

 microtime

-0.13

 ç¦

-0.13

Ĥ

-0.13

 Bench

-0.13

cas

-0.13

POSITIVE LOGITS

aghan

0.16

azing

0.16

CurrentValue

0.16

conde

0.16

venta

0.15

 serm

0.15

ayah

0.14

sons

0.14

rschein

0.14

ansas

0.14

Activations Density 0.044%

specific numbers or numeric sequences

No Comments

No Known Activations