INDEX

Explanations

dialogue transitions and conversational markers

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

aspers

-0.16

edin

-0.15

alc

-0.15

ë¶ģ

-0.14

ceae

-0.14

niejs

-0.14

sons

-0.14

zac

-0.13

ÏĮÏģ

-0.13

 porr

-0.13

POSITIVE LOGITS

erset

0.15

oron

0.15

onto

0.15

ÛĮØ±Ùĩ

0.14

«

0.14

hea

0.14

áº¿

0.13

 Ø®Ø§Ú©

0.13

Ð¾Ð¼Ð°

0.13

Activations Density 0.089%

dialogue transitions and conversational markers

No Comments

No Known Activations