INDEX

Explanations

references to individuals and entities associated with notable products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

amarin

-0.17

ãĤĪ

-0.17

 spre

-0.16

-0.15

avl

-0.15

 pstmt

-0.15

 yÃªn

-0.15

Ð»Ð°Ð¼Ð¸

-0.14

upert

-0.14

POSITIVE LOGITS

Col

0.18

Col

0.16

TC

0.16

ãĥĶãĥ¼

0.15

-Col

0.15

ÐºÐ¾Ð»

0.15

ch

0.15

_col

0.15

apper

0.14

ieren

0.14

Activations Density 0.033%

references to individuals and entities associated with notable products or services

No Comments

No Known Activations