INDEX

Explanations

numerical data and references to legal or financial concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

SEG

-0.15

ora

-0.14

 Kushner

-0.14

IDES

-0.14

eti

-0.14

_ValueChanged

-0.14

 tast

-0.14

 unreal

-0.14

POSITIVE LOGITS

neau

0.16

ì¡

0.15

(cin

0.15

 Natural

0.15

jure

0.15

upply

0.14

fraction

0.14

Ä±sÄ±r

0.14

theid

0.14

ablish

0.14

Activations Density 0.004%

numerical data and references to legal or financial concepts

No Comments

No Known Activations