INDEX

Explanations

references to storytelling and narrative development

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

exterity

-0.16

ÑĢÐ°Ð²Ð°

-0.14

ÙĪØ§ÙĨ

-0.14

ãİ

-0.14

atz

-0.14

uyla

-0.14

æı

-0.14

ABCDE

-0.14

oldur

-0.14

POSITIVE LOGITS

us

0.15

æĪĲ

0.15

 Rear

0.15

igg

0.15

oj

0.14

ine

0.14

ump

0.14

imon

0.14

upt

0.14

ahan

0.14

Activations Density 0.350%

references to storytelling and narrative development

No Comments

No Known Activations