INDEX

Explanations

mathematical symbols and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ascus

-0.16

iali

-0.15

 Gould

-0.15

asco

-0.14

asser

-0.14

-placeholder

-0.14

elden

-0.14

æ®Ĭ

-0.14

--[[

-0.14

eldon

-0.13

POSITIVE LOGITS

.python

0.16

niÅ¾

0.14

InView

0.14

æĳ

0.14

Ð¸Ñī

0.14

itsu

0.13

Sv

0.13

åĳ½

0.13

instr

0.13

ï¿

0.13

Activations Density 0.075%

mathematical symbols and notations

No Comments

No Known Activations