INDEX

Explanations

words related to acknowledgment or recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ature

-0.16

resh

-0.16

iscard

-0.16

ura

-0.15

brook

-0.15

edback

-0.15

ÅĽmy

-0.15

rey

-0.15

urge

-0.15

iggins

-0.14

POSITIVE LOGITS

ably

0.20

èŃĺ

0.17

 recognize

0.17

/address

0.16

 importance

0.16

Recogn

0.15

recogn

0.15

ances

0.15

 Recogn

0.15

fait

0.15

Activations Density 0.027%

words related to acknowledgment or recognition

No Comments

No Known Activations