INDEX

Explanations

the word "short" in various contexts

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

umu

-0.15

hra

-0.15

à¸¥à¸°

-0.14

ome

-0.14

erland

-0.14

/>";↵

-0.13

åºŃ

-0.13

dsl

-0.13

 discretion

-0.13

POSITIVE LOGITS

erli

0.17

-short

0.17

-lived

0.17

(short

0.16

ened

0.16

night

0.15

enek

0.15

 ngáº¯n

0.15

listed

0.15

codes

0.15

Activations Density 0.027%

the word "short" in various contexts

No Comments

No Known Activations