INDEX

Explanations

mentions of months, particularly their names and related numerical representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ToWorld

-0.16

Ã»

-0.15

imus

-0.15

ÑıÐ¶

-0.14

paque

-0.14

agna

-0.14

infeld

-0.14

 alph

-0.14

upo

-0.14

Ã©rica

-0.14

POSITIVE LOGITS

nox

0.15

lich

0.15

uma

0.14

arnation

0.14

Ro

0.14

 double

0.14

erras

0.13

_ast

0.13

ams

0.13

ocol

0.13

Activations Density 0.014%

mentions of months, particularly their names and related numerical representations

No Comments

No Known Activations