INDEX

Explanations

references to harmful environmental substances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

emark

-0.15

verb

-0.14

êµ´

-0.14

engan

-0.13

eration

-0.13

til

-0.13

eu

-0.13

 seeming

-0.13

ansion

-0.13

POSITIVE LOGITS

-components

0.17

 Ø§Ø¬Ø±

0.16

 components

0.16

ÑĨÐ²ÐµÑĤ

0.15

/colors

0.15

aceous

0.15

lint

0.15

CLUDING

0.14

adm

0.14

 substances

0.14

Activations Density 0.121%

references to harmful environmental substances

No Comments

No Known Activations