INDEX

Explanations

terms related to public relations and communications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

oo

-0.16

igg

-0.16

 Gunn

-0.14

ÐŁÐļ

-0.14

ew

-0.14

 messenger

-0.14

cif

-0.14

 Minister

-0.14

raj

-0.14

vent

-0.13

POSITIVE LOGITS

Äįan

0.18

orque

0.15

wagon

0.15

tul

0.14

autoload

0.14

ACC

0.14

Å¡ov

0.14

rou

0.14

Å¾el

0.14

rsp

0.14

Activations Density 0.048%

terms related to public relations and communications

No Comments

No Known Activations