INDEX

Explanations

questions or inquiries about actions and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

itzer

-0.17

currently

-0.15

able

-0.14

aylight

-0.14

Äį

-0.14

izedName

-0.14

Ø§ÙģÙĬØ©

-0.14

DDL

-0.14

alley

-0.14

izer

-0.14

POSITIVE LOGITS

actic

0.20

 originally

0.19

 yesterday

0.18

nt

0.18

 formerly

0.17

 recently

0.17

ÅĽmy

0.16

 Ð±Ñĭ

0.16

 jsem

0.16

rops

0.15

Activations Density 0.081%

questions or inquiries about actions and events

No Comments

No Known Activations