INDEX

Explanations

phrases related to analysis and development processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

è©²

-0.14

elo

-0.14

Ð°Ð½ÑģÐ¸

-0.13

è¯¥

-0.13

 itself

-0.13

::~

-0.12

ÂĿ

-0.12

ÑĦÐ¾ÑĢÐ¼Ð¸

-0.12

him

-0.12

esel

-0.12

POSITIVE LOGITS

 them

0.76

å®ĥä»¬

0.76

 they

0.70

they

0.62

them

0.59

 They

0.59

They

0.59

 Ð¾Ð½Ð¸

0.57

 ihnen

0.56

 mereka

0.56

Activations Density 1.161%

phrases related to analysis and development processes

No Comments

No Known Activations