INDEX

Explanations

geographic locations and landmarks

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

adio

-0.16

agna

-0.16

agher

-0.16

ritch

-0.15

 escorte

-0.14

agne

-0.14

 Sachs

-0.14

oleÄį

-0.14

 Scala

-0.14

erset

-0.14

POSITIVE LOGITS

 Ø§ÙĦØªØ¬

0.15

 ì°©

0.14

 Richardson

0.14

 Cand

0.14

onen

0.14

erule

0.14

Ast

0.13

errer

0.13

ast

0.13

imir

0.13

Activations Density 0.051%

geographic locations and landmarks

No Comments

No Known Activations