INDEX

Explanations

references to agreements or treaties

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

ãģĹãĤĥ

-0.17

yte

-0.16

 lÃ²ng

-0.16

oni

-0.15

æĽ

-0.15

 cork

-0.14

pons

-0.14

Ð´Ð¾Ð²

-0.14

Loy

-0.14

 ifndef

-0.14

POSITIVE LOGITS

ance

0.16

anse

0.15

erras

0.15

afen

0.14

peat

0.14

ukan

0.14

ingham

0.14

oli

0.13

zeit

0.13

uche

0.13

Activations Density 0.006%

references to agreements or treaties

No Comments

No Known Activations