INDEX

Explanations

references to location or positional context

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

lest

-0.16

 BindingFlags

-0.15

ÄĽn

-0.15

 gram

-0.15

eroon

-0.14

obraz

-0.14

ossa

-0.14

lesc

-0.14

zem

-0.13

ximo

-0.13

POSITIVE LOGITS

FO

0.15

ieten

0.14

 nackte

0.14

nex

0.14

 tort

0.13

ernes

0.13

eniable

0.13

razil

0.13

 Peoples

0.13

Evt

0.13

Activations Density 0.024%

references to location or positional context

No Comments

No Known Activations