INDEX

Explanations

noun phrases indicating existence or identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

alam

-0.16

cad

-0.14

chu

-0.14

forge

-0.14

rees

-0.13

office

-0.13

.va

-0.13

sez

-0.13

Anywhere

-0.13

illon

-0.13

POSITIVE LOGITS

.slim

0.19

akin

0.16

hlen

0.16

ulos

0.15

 ÙĦÙĨ

0.15

opsis

0.15

Ã¼tÃ¼n

0.14

.INSTANCE

0.14

opot

0.14

IMARY

0.14

Activations Density 0.020%

noun phrases indicating existence or identity

No Comments

No Known Activations