INDEX

Explanations

phrases involving connections or relationships between actions and their impact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

aeda

-0.15

Disposition

-0.15

uards

-0.14

Ð»Ð°ÑģÑĤÐ¸

-0.14

estre

-0.14

Orm

-0.14

ãĥ¼ãĥĵ

-0.14

aised

-0.14

.did

-0.13

èµ·

-0.13

POSITIVE LOGITS

onto

0.18

 instead

0.16

 tongue

0.15

 allow

0.15

 onto

0.15

let

0.15

 into

0.14

enie

0.14

 become

0.14

opt

0.14

Activations Density 0.213%

phrases involving connections or relationships between actions and their impact

No Comments

No Known Activations