INDEX

Explanations

mentions of "Ro" followed by various letters or numbers, likely related to product names or brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ÙĪÙĨØ§

-0.16

ogl

-0.16

Ã¤Ã¤n

-0.15

ures

-0.14

urally

-0.14

:numel

-0.14

ifo

-0.14

ulong

-0.14

Î¼ÎŃÎ½

-0.14

lexport

-0.14

POSITIVE LOGITS

estone

0.16

emiz

0.15

inc

0.15

Ĥæķ°

0.14

wing

0.14

oky

0.14

est

0.14

ÌĪ

0.14

emoth

0.14

Dub

0.14

Activations Density 0.007%

mentions of "Ro" followed by various letters or numbers, likely related to product names or brands

No Comments

No Known Activations