INDEX

Explanations

adverbs that indicate degree or frequency

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

VML

-0.17

ëįĶëĭĪ

-0.15

Î³ÎºÎ±

-0.15

ãģķãĤī

-0.15

ÑĢÑĸÐ¹

-0.14

keley

-0.14

\grid

-0.14

 ?><?

-0.14

kir

-0.14

ilio

-0.14

POSITIVE LOGITS

Gol

0.15

loc

0.15

 Julian

0.14

 tslint

0.14

Roh

0.13

Dol

0.13

à¹ģà¸ķ

0.13

 Katz

0.13

borg

0.13

 sphere

0.13

Activations Density 0.127%

adverbs that indicate degree or frequency

No Comments

No Known Activations