INDEX

Explanations

numeric values and percentages associated with data reporting

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

inger

-0.19

opoulos

-0.17

igm

-0.16

 hoop

-0.15

ÌĤ

-0.15

 joint

-0.14

/cgi

-0.14

ureau

-0.14

-model

-0.14

 House

-0.14

POSITIVE LOGITS

Touches

0.16

parms

0.15

acier

0.15

uforia

0.15

kyt

0.15

AREST

0.15

armor

0.14

aÅ¼

0.14

Comparer

0.14

apgolly

0.14

Activations Density 0.082%

numeric values and percentages associated with data reporting

No Comments

No Known Activations