INDEX

Explanations

expressions of uncertainty or disbelief

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

 voksen

-0.15

 Frequ

-0.14

Vtbl

-0.14

amber

-0.14

æ»

-0.13

upplier

-0.13

 Ð³Ð¾ÑĢ

-0.13

_PTR

-0.13

 proport

-0.13

Î³ÏīÎ½

-0.13

POSITIVE LOGITS

0.14

mit

0.13

 escap

0.13

-plus

0.13

 Crow

0.13

 going

0.13

aco

0.13

rett

0.13

Activations Density 0.015%

expressions of uncertainty or disbelief

No Comments

No Known Activations