INDEX

Explanations

words and terms related to sedatives and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 Hust

-0.16

ertz

-0.14

frame

-0.14

-0.13

_Destroy

-0.13

à¸±à¸Ļà¸ĺ

-0.13

Ã³j

-0.13

çķ°

-0.13

POSITIVE LOGITS

ACHI

0.18

ibel

0.17

Ach

0.15

Sed

0.15

trap

0.15

ADDE

0.15

 Crosby

0.15

ÑħÐ¸

0.15

kah

0.15

 flattened

0.14

Activations Density 0.008%

words and terms related to sedatives and their effects

No Comments

No Known Activations