INDEX

Explanations

terms related to reinforcement learning and modeling concepts

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

peria

-0.18

arella

-0.15

uzz

-0.15

ãĤ

-0.15

lein

-0.15

processable

-0.15

indrome

-0.15

modo

-0.14

elin

-0.14

staking

-0.14

POSITIVE LOGITS

 slate

0.15

con

0.15

 action

0.15

Han

0.15

 state

0.15

Jeg

0.14

lund

0.14

AGENT

0.14

SCO

0.14

ag

0.14

Activations Density 0.014%

terms related to reinforcement learning and modeling concepts

No Comments

No Known Activations