INDEX

Explanations

pronouns and demonstrative pronouns indicating proximity or reference

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

infos

-0.16

ëħĦìĹĲëĬĶ

-0.14

dac

-0.14

 trif

-0.14

Ã¢ncia

-0.14

uddle

-0.14

Wak

-0.13

.snp

-0.13

isas

-0.13

ank

-0.13

POSITIVE LOGITS

oker

0.17

ould

0.14

.TryParse

0.14

ï¿

0.14

¤í

0.14

isd

0.13

xl

0.13

åłĤ

0.13

Activations Density 0.006%

pronouns and demonstrative pronouns indicating proximity or reference

No Comments

No Known Activations