INDEX

Explanations

elements that indicate an action or state in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ÌĨ

-0.16

alla

-0.15

ÙĦØ·

-0.14

\Table

-0.14

íĪ¬

-0.14

owi

-0.14

esp

-0.14

rÃ½

-0.13

efd

-0.13

ouz

-0.13

POSITIVE LOGITS

 onDataChange

0.16

EC

0.15

unde

0.15

ifax

0.15

 ngoáº¡i

0.15

hec

0.15

Ã³ng

0.14

Ã´

0.14

uom

0.14

tie

0.14

Activations Density 0.001%

elements that indicate an action or state in various contexts

No Comments

No Known Activations