INDEX

Explanations

names of restaurants and dining establishments

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

è¸

-0.16

thon

-0.16

Probe

-0.15

ÏīÎ¼Î±

-0.15

irs

-0.14

iode

-0.14

pcodes

-0.14

cott

-0.14

 Attribution

-0.14

ensis

-0.13

POSITIVE LOGITS

sys

0.15

itty

0.15

VD

0.14

 Crom

0.14

crop

0.14

itor

0.13

_KEYS

0.13

_Base

0.13

dov

0.13

AP

0.13

Activations Density 0.123%

names of restaurants and dining establishments

No Comments

No Known Activations