INDEX

Explanations

the use of the phrase "been" indicating ongoing or completed actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ladu

-0.16

iol

-0.15

 mainland

-0.15

uen

-0.15

 fastball

-0.14

 motto

-0.14

uisse

-0.14

rung

-0.14

 ÑĢÐ¾Ð·Ðº

-0.14

-0.13

POSITIVE LOGITS

dera

0.16

acea

0.15

 Suff

0.14

]={↵

0.14

íĦ°

0.14

achu

0.14

afen

0.14

olf

0.14

mlink

0.14

ÑĤÑĮ

0.13

Activations Density 0.032%

the use of the phrase "been" indicating ongoing or completed actions

No Comments

No Known Activations