INDEX

Explanations

instances of the word "all" used 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

Į

-0.16

ulers

-0.15

ely

-0.15

Ìĥ

-0.15

esh

-0.14

eless

-0.14

es

-0.14

deme

-0.14

ember

-0.14

edis

-0.14

POSITIVE LOGITS

iese

0.18

Bindable

0.16

ARP

0.15

igator

0.15

igators

0.14

-ÑĤÐ°ÐºÐ¸

0.14

uminum

0.14

bedo

0.14

mai

0.14

iah

0.13

Activations Density 0.022%

instances of the word "all" used in various contexts

No Comments

No Known Activations