INDEX

Explanations

mentions of educational institutions, specifically Georgetown University

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 Ethnic

-0.15

abis

-0.15

ãĥ¬ãĥĥãĥĪ

-0.15

lej

-0.14

 respect

-0.14

ethnic

-0.14

enstein

-0.14

ETA

-0.14

aban

-0.14

ÑıÑĤÑĮ

-0.14

POSITIVE LOGITS

pta

0.17

chu

0.15

0.14

ORIES

0.14

Ð»ÐºÐ¸

0.14

lar

0.14

LEAN

0.14

orus

0.14

è¾ĳ

0.14

Activations Density 0.001%

mentions of educational institutions, specifically Georgetown University

No Comments

No Known Activations