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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

oris

-0.16

on

-0.16

anja

-0.15

AWN

-0.15

anje

-0.14

onne

-0.14

onen

-0.14

elligence

-0.14

oner

-0.13

¸

-0.13

POSITIVE LOGITS

 guise

0.17

 umbrella

0.15

ady

0.15

wing

0.15

unf

0.15

 wings

0.14

_ttl

0.14

uard

0.14

ÏĦÎ±Î½

0.14

whel

0.14

Activations Density 0.023%

occurrences of the word "the."

No Comments

No Known Activations