INDEX

Explanations

entities and key terms related to organization and categorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

tc

-0.15

lue

-0.15

 cone

-0.15

uide

-0.15

echa

-0.14

irket

-0.14

ologue

-0.14

åİĨ

-0.14

ãĤ½ãĥ³

-0.14

_aa

-0.13

POSITIVE LOGITS

ilos

0.16

 Opcode

0.16

edido

0.15

ostel

0.15

uggage

0.15

kid

0.15

atsby

0.14

igos

0.14

_PTR

0.14

edin

0.14

Activations Density 0.022%

entities and key terms related to organization and categorization

No Comments

No Known Activations