INDEX

Explanations

references to time, specifically past events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ovny

-0.16

letter

-0.15

anner

-0.14

orsk

-0.14

.utilities

-0.14

oad

-0.14

bulk

-0.14

agedList

-0.14

hid

-0.14

pad

-0.14

POSITIVE LOGITS

ichni

0.15

elo

0.15

ÑĢÐ´

0.15

reed

0.15

evin

0.15

ideo

0.15

INCT

0.14

 Highlander

0.14

urai

0.14

quo

0.14

Activations Density 0.015%

references to time, specifically past events

No Comments

No Known Activations