INDEX

Explanations

terms related to objects or entities involved in logistical or structural contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

aires

-0.20

ãģ¨ãģį

-0.20

erson

-0.19

airs

-0.19

variable

-0.19

urator

-0.19

chin

-0.19

erman

-0.18

aire

-0.18

variably

-0.17

POSITIVE LOGITS

ãģ¹ãģį

0.27

itage

0.20

hythm

0.20

hyth

0.20

anged

0.19

ithmetic

0.19

bitrary

0.19

naments

0.18

iginal

0.18

devil

0.17

Activations Density 0.196%

terms related to objects or entities involved in logistical or structural contexts

No Known Activations