INDEX

Explanations

references to responses and reactions 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

resse

-0.17

oya

-0.16

ernet

-0.15

ery

-0.15

vet

-0.15

igrations

-0.14

reece

-0.14

WISE

-0.14

losures

-0.14

icago

-0.14

POSITIVE LOGITS

/response

0.20

<|begin_of_text|>

0.18

ToSelector

0.18

(Response

0.17

ivate

0.16

=response

0.16

.sendRedirect

0.15

aldo

0.15

ively

0.15

ero

0.15

Activations Density 0.042%

references to responses and reactions in various contexts

No Comments

No Known Activations