INDEX

Explanations

references to various content and sections of a website

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

 ÙħØ´Ø§Ø±Ú©Øª

-0.15

ott

-0.14

 Sidd

-0.14

Ã¡rio

-0.14

reso

-0.14

ensis

-0.14

errick

-0.13

áº¥n

-0.13

Heg

-0.13

elivery

-0.13

POSITIVE LOGITS

.Resolve

0.15

ONS

0.14

å®³

0.14

.oc

0.14

ovky

0.14

íķĺìļ°

0.14

rch

0.14

.BorderFactory

0.14

cem

0.14

ainen

0.14

Activations Density 0.059%

references to various content and sections of a website

No Comments

No Known Activations