INDEX

Explanations

occurrences of the word "I" and its related forms, indicating a focus on personal experiences or perspectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

pong

-0.14

wand

-0.14

 AppState

-0.14

fans

-0.13

Ã¶k

-0.13

lou

-0.13

-us

-0.13

APPER

-0.13

WARDED

-0.13

lk

-0.13

POSITIVE LOGITS

ample

0.17

0.16

 Morav

0.15

 alike

0.15

ager

0.14

ihil

0.14

HAL

0.14

istr

0.14

SBATCH

0.14

.MouseAdapter

0.13

Activations Density 0.015%

occurrences of the word "I" and its related forms, indicating a focus on personal experiences or perspectives

No Comments

No Known Activations