INDEX

Explanations

references to generated code or components within a programming context

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

bable

-0.17

ylvania

-0.17

afil

-0.15

 fiber

-0.15

 overd

-0.15

htags

-0.14

assen

-0.14

phia

-0.14

ettle

-0.14

umbo

-0.14

POSITIVE LOGITS

TRL

0.16

tas

0.16

 endregion

0.15

-UA

0.15

iku

0.14

tro

0.14

.trip

0.14

Kho

0.13

.observable

0.13

amu

0.13

Activations Density 0.002%

references to generated code or components within a programming context

No Comments

No Known Activations