INDEX

Explanations

occurrences of the definite article "the" and other specific contextual clues within technical or procedural content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

edom

-0.17

bish

-0.15

ushman

-0.15

orning

-0.14

ofile

-0.14

adle

-0.14

inh

-0.14

ematic

-0.14

ulace

-0.13

ymb

-0.13

POSITIVE LOGITS

LookAndFeel

0.16

inded

0.16

hai

0.14

Î»ÏĮÎ³

0.14

acular

0.14

vre

0.14

olar

0.14

 Weed

0.14

tha

0.13

ovy

0.13

Activations Density 0.009%

occurrences of the definite article "the" and other specific contextual clues within technical or procedural content

No Comments

No Known Activations