INDEX

Explanations

references to different types of seating arrangements

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

ĥĿ

-0.15

ooks

-0.15

ince

-0.15

inda

-0.15

ogl

-0.14

ative

-0.14

 Empty

-0.14

ÃŃd

-0.14

fulness

-0.13

 Muscle

-0.13

POSITIVE LOGITS

apus

0.17

IZER

0.15

_LAYER

0.15

hol

0.15

holm

0.15

áº«

0.15

posables

0.15

 targetType

0.15

ipt

0.14

oton

0.14

Activations Density 0.004%

references to different types of seating arrangements

No Comments

No Known Activations