INDEX

Explanations

names of films and their associated ratings

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

ingle

-0.16

 nobody

-0.15

ifton

-0.15

 none

-0.14

 None

-0.14

à¥įà¤®à¤ļ

-0.14

ullan

-0.14

alim

-0.14

 Blind

-0.14

Ã¤t

-0.13

POSITIVE LOGITS

REW

0.17

ÐµÑĢÐ±

0.16

"nil

0.15

 crest

0.15

kili

0.14

.ResponseWriter

0.14

fan

0.14

OffsetTable

0.14

Ëĺ

0.14

agma

0.14

Activations Density 0.014%

names of films and their associated ratings

No Comments

No Known Activations