INDEX

Explanations

phrases indicating the inclusion or addition of various elements or components

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ulla

-0.15

DAQ

-0.15

èĥ¶

-0.15

IGN

-0.15

_CODES

-0.15

ç·ı

-0.14

 HEAP

-0.14

qt

-0.14

 Griff

-0.13

hei

-0.13

POSITIVE LOGITS

0.16

swer

0.15

 ãĥĬ

0.15

0.14

çĶ²

0.14

les

0.14

è·Ŀ

0.14

 Katz

0.14

anders

0.14

_nth

0.13

Activations Density 0.026%

phrases indicating the inclusion or addition of various elements or components

No Comments

No Known Activations