INDEX

Explanations

queries and problem-solving phrases

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

ancia

-0.16

ãģ°ãģĭãĤĬ

-0.14

pose

-0.14

rak

-0.14

avenport

-0.14

por

-0.14

 simpl

-0.14

pare

-0.14

 ÑĦÐ¾ÑĢ

-0.14

-0.13

POSITIVE LOGITS

pedia

0.15

sink

0.15

 Baum

0.15

 subplot

0.14

urum

0.14

ipp

0.14

NetMessage

0.14

éı

0.14

áº¡ch

0.14

roids

0.13

Activations Density 0.042%

queries and problem-solving phrases

No Comments

No Known Activations