INDEX

Explanations

instances of the word "similarly" indicating comparisons or parallels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

mpz

-0.18

umas

-0.16

ÑģÐµ

-0.15

Ð¾ÐºÐ¾Ð»

-0.15

mony

-0.15

ãİ

-0.15

ÑĥÑĢÐ¸

-0.15

 Ð¾ÑģÑĮ

-0.14

_Utils

-0.14

Pru

-0.14

POSITIVE LOGITS

atis

0.15

 other

0.15

II

0.15

Sy

0.15

 vain

0.14

ÎŃÏģÎ³

0.14

Past

0.14

dis

0.14

Sh

0.14

 edge

0.14

Activations Density 0.007%

instances of the word "similarly" indicating comparisons or parallels

No Comments

No Known Activations