INDEX

Explanations

terms related to frequency and regularity of actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

otte

-0.18

 Ð²Ð·

-0.16

kova

-0.16

zion

-0.16

oval

-0.16

iaux

-0.15

à¤¸à¤²

-0.14

requestCode

-0.14

kovi

-0.14

 VÅ¡ech

-0.14

POSITIVE LOGITS

 frequency

0.16

0.15

à¤Ĥà¤¸

0.15

 convo

0.15

 Declarations

0.15

 Frequency

0.15

0.14

é¢ĳæ¬¡

0.14

akash

0.14

 Rare

0.14

Activations Density 0.220%

terms related to frequency and regularity of actions

No Comments

No Known Activations