INDEX

Explanations

references to academic titles or doctorates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

tam

-0.16

lius

-0.16

ts

-0.14

coli

-0.14

 Murdoch

-0.14

andi

-0.13

-pt

-0.13

ensen

-0.13

enas

-0.13

POSITIVE LOGITS

aaS

0.15

raries

0.14

eyen

0.14

adal

0.14

Dod

0.14

Latch

0.14

ufe

0.13

ptime

0.13

oram

0.13

ãĥĨãĥ«

0.13

Activations Density 0.019%

references to academic titles or doctorates

No Comments

No Known Activations