INDEX

Explanations

occurrences of the word "Gorilla" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ined

-0.16

ikat

-0.16

 concurrent

-0.15

atern

-0.15

IED

-0.15

 Sheridan

-0.15

 spectral

-0.14

pekt

-0.14

Ð±Ð¾ÑĢÐ°

-0.14

POSITIVE LOGITS

illas

0.30

illa

0.28

ILLA

0.21

izia

0.21

ansson

0.19

ONTAL

0.19

izont

0.19

leston

0.19

ordo

0.18

untu

0.18

Activations Density 0.008%

occurrences of the word "Gorilla" in various contexts

No Comments

No Known Activations