INDEX

Explanations

concepts related to long-term versus short-term thinking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

astle

-0.16

 Franco

-0.16

 aisle

-0.15

ÏĥÎ¹Î±

-0.15

irim

-0.14

ãĤ¯ãĥ©

-0.14

_spell

-0.14

 magic

-0.14

CHANNEL

-0.14

annels

-0.14

POSITIVE LOGITS

ori

0.17

0.16

0.15

hoff

0.15

 tomorrow

0.14

getQuery

0.14

arsi

0.14

bras

0.14

Activations Density 0.198%

concepts related to long-term versus short-term thinking

No Comments

No Known Activations