INDEX

Explanations

mentions of "rope" and related terms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

-0.17

jon

-0.17

ickerView

-0.16

Æł

-0.16

ropol

-0.16

Ð»Ð¸ÑĤ

-0.16

ÑĢÐ¾Ð¼

-0.15

rompt

-0.14

icken

-0.14

widgets

-0.14

POSITIVE LOGITS

age

0.16

undi

0.15

/ns

0.14

 Forbidden

0.14

sp

0.14

Ã¸

0.14

/thumb

0.13

ament

0.13

head

0.13

Forbidden

0.13

Activations Density 0.010%

mentions of "rope" and related terms

No Comments

No Known Activations