INDEX

Explanations

occurrences of the word "for" 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 @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

/Application

-0.15

eless

-0.15

ilton

-0.14

ReturnValue

-0.14

ixer

-0.14

flare

-0.13

opoly

-0.13

à¸§à¸Ļ

-0.13

ilk

-0.13

poke

-0.13

POSITIVE LOGITS

Ãªt

0.20

asm

0.15

imson

0.15

apan

0.15

bao

0.15

Ð»ÑĸÑĤ

0.14

lage

0.14

Ð¸Ð»ÑĮ

0.14

ds

0.14

azio

0.14

Activations Density 0.115%

occurrences of the word "for" in various contexts

No Comments

No Known Activations