INDEX

Explanations

first-person pronouns and expressions of personal opinion or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 wonder

-0.16

ãĥ¼ãĥª

-0.15

 migrationBuilder

-0.15

cratch

-0.15

estone

-0.15

ãģĿãģĨãģª

-0.14

ocado

-0.14

leur

-0.14

erton

-0.14

onnement

-0.14

POSITIVE LOGITS

CESS

0.15

osh

0.15

ya

0.14

 previously

0.14

yan

0.14

ades

0.14

ansa

0.14

hem

0.13

ede

0.13

may

0.13

Activations Density 0.045%

first-person pronouns and expressions of personal opinion or experiences

No Comments

No Known Activations