INDEX

Explanations

phrases related to proportions or distributions

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

ed

-0.16

çĽ¤

-0.15

 Crate

-0.15

ling

-0.15

edBy

-0.15

ellar

-0.14

inal

-0.14

CCI

-0.14

ifest

-0.14

POSITIVE LOGITS

ptune

0.14

abelle

0.14

Ã¶g

0.14

oin

0.14

(SS

0.14

idad

0.13

errat

0.13

untime

0.13

unsch

0.13

us

0.13

Activations Density 0.039%

phrases related to proportions or distributions

No Comments

No Known Activations