INDEX

Explanations

references to the name "Rob" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ighb

-0.16

ÏĢÎ¿Ïį

-0.15

endance

-0.14

iard

-0.14

kh

-0.14

finalize

-0.14

Configurer

-0.14

KT

-0.14

ëĿ½

-0.14

 Ð¼Ð¸Ð½Ð¸Ð¼

-0.13

POSITIVE LOGITS

ust

0.29

bers

0.29

lox

0.27

bery

0.26

bing

0.25

ocop

0.25

esp

0.23

bin

0.23

ber

0.23

yn

0.23

Activations Density 0.012%

references to the name "Rob" and its variations in various contexts

No Comments

No Known Activations