INDEX

Explanations

occurrences of the word "The"

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

rl

-0.15

oldt

-0.15

poh

-0.14

azel

-0.14

weg

-0.14

yer

-0.14

enstein

-0.14

uddenly

-0.14

adil

-0.13

IGO

-0.13

POSITIVE LOGITS

undef

0.20

 Wall

0.18

ewan

0.17

eden

0.16

 Daly

0.15

 Washington

0.15

aign

0.14

InParameter

0.14

 Hass

0.14

issen

0.14

Activations Density 0.053%

occurrences of the word "The"

No Comments

No Known Activations