INDEX

Explanations

references to power and influence, particularly in the context of actions and effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ãģ°

-0.17

/stdc

-0.16

tes

-0.15

Ð¸ÑģÐ»Ð¾Ð²

-0.15

Ð¶Ð´

-0.15

á»Ĩ

-0.15

mentions

-0.15

authorize

-0.15

hop

-0.15

irm

-0.14

POSITIVE LOGITS

0.19

aged

0.17

inkel

0.17

ered

0.17

 lÆ°á»£ng

0.17

ivel

0.16

ful

0.15

chan

0.15

lessly

0.15

age

0.15

Activations Density 0.041%

references to power and influence, particularly in the context of actions and effects

No Comments

No Known Activations