INDEX

Explanations

discussions about human complexity and the influence of various factors on behavior

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ÅĻet

-0.17

annis

-0.15

à¤¾à¤¯à¤¨

-0.15

emporary

-0.14

ayan

-0.14

ikip

-0.14

ongan

-0.14

/light

-0.14

entai

-0.14

reate

-0.14

POSITIVE LOGITS

 Sext

0.16

tro

0.14

FW

0.14

 decentral

0.14

Umb

0.14

iat

0.14

ãĤ·ãĥ£

0.14

æĳ¸

0.14

iyat

0.14

 situation

0.13

Activations Density 0.437%

discussions about human complexity and the influence of various factors on behavior

No Comments

No Known Activations